© 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. 124151
    Prev
    Next
    INDEX
    Explanations

    comparative phrases or expressions indicating superiority or preference

    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
    sort
    -0.07
    amente
    -0.07
    är
    -0.07
    serv
    -0.06
    ends
    -0.06
    own
    -0.06
    dent
    -0.06
    laus
    -0.06
    sf
    -0.06
    454
    -0.06
    POSITIVE LOGITS
    ls
    0.08
    atology
    0.07
    abor
    0.07
    sgiving
    0.07
    abez
    0.07
    пÑĢав
    0.07
    essa
    0.07
    रल
    0.07
     ofType
    0.07
    lers
    0.06
    Activations Density 0.004%

    No Known Activations