© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-32K
    11. 19878
    Prev
    Next
    INDEX
    Explanations

    verbs associated with quantity or addition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Looking at the activations, this neuron activates weakly (values around 0.3-0.4) on a variety of tokens across different contexts, with the highest activation being 0.463 on " from" in the first example. The neuron appears to find

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orr
    -0.15
    ajo
    -0.15
    менно
    -0.15
    ipes
    -0.14
    élé
    -0.14
    _stand
    -0.13
     #+#
    -0.13
    ãģĤãģĤ
    -0.13
     Spo
    -0.13
    ért
    -0.13
    POSITIVE LOGITS
    avan
    0.19
    .blob
    0.16
    inel
    0.15
     Duy
    0.15
    572
    0.15
    inator
    0.14
    uce
    0.14
    aty
    0.14
    etler
    0.14
    odate
    0.14
    Activations Density 0.000%

    No Known Activations