© 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. 17-LLAMASCOPE-RES-131K
    11. 118816
    Prev
    Next
    INDEX
    Explanations

    references to acknowledgment and respect for Aboriginal and Torres Strait Islander peoples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fila
    -0.08
    reau
    -0.07
    黨
    -0.07
    INES
    -0.07
    EXTERN
    -0.06
    MeasureSpec
    -0.06
    ж
    -0.06
    quet
    -0.06
     Ow
    -0.06
     COMMON
    -0.06
    POSITIVE LOGITS
    .expression
    0.06
    ufs
    0.06
    quia
    0.06
     dias
    0.06
    icont
    0.06
    zas
    0.06
    pha
    0.06
    æĸĻ
    0.06
    instein
    0.06
    $LANG
    0.06
    Activations Density 0.002%

    No Known Activations