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

    Neuronpedia

    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. 9-LLAMASCOPE-RES-32K
    11. 7054
    Prev
    Next
    INDEX
    Explanations

    contrasts between small and large tasks, as well as the conditions and factors affecting various situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    άκ
    -0.17
    rite
    -0.16
    å¬
    -0.16
    ester
    -0.15
     keyof
    -0.15
    ylan
    -0.15
    reau
    -0.15
    onom
    -0.14
     tek
    -0.14
    yp
    -0.14
    POSITIVE LOGITS
     Rogers
    0.17
    é½
    0.14
    letal
    0.14
     Mango
    0.14
     specialty
    0.13
    phalt
    0.13
    theid
    0.13
    udos
    0.13
    romo
    0.13
    izoph
    0.13
    Activations Density 0.072%

    No Known Activations