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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9250
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating actions and sequences in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    etro
    -0.15
    raÄį
    -0.15
    opa
    -0.15
    Æ¡i
    -0.14
    ORB
    -0.14
    oš
    -0.14
    icles
    -0.14
    оÑı
    -0.14
    Å¡la
    -0.13
    _amp
    -0.13
    POSITIVE LOGITS
    ease
    0.14
    iola
    0.14
    лад
    0.14
    regor
    0.14
    @student
    0.14
    bove
    0.14
    Forge
    0.14
    ÏĥÏĦα
    0.13
    reu
    0.13
     banner
    0.13
    Activations Density 0.006%

    No Known Activations