© 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 EvalsExportsinterp-engineNEWAPI 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. 42060
    Prev
    Next
    INDEX
    Explanations

    references to notable or distinguished individuals and their achievements

    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
     Sexo
    -0.07
    emoc
    -0.07
    бÑĢа
    -0.07
    овеÑĢ
    -0.07
    tres
    -0.07
    окÑģи
    -0.07
    enums
    -0.06
    amework
    -0.06
    idunt
    -0.06
    asp
    -0.06
    POSITIVE LOGITS
    اÙĩد
    0.06
     Sad
    0.06
     figure
    0.06
     architekt
    0.06
    íħ
    0.06
     former
    0.06
     careers
    0.06
    rippling
    0.06
     arch
    0.06
     oct
    0.06
    Activations Density 0.022%

    No Known Activations