© 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. 107811
    Prev
    Next
    INDEX
    Explanations

    various types and classifications, particularly in scientific or technical contexts

    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
    aphore
    -0.06
    xn
    -0.06
    ières
    -0.06
    iere
    -0.06
    инÑĥ
    -0.06
    å±Ĭ
    -0.06
    endants
    -0.06
     Mehr
    -0.06
     prostitutas
    -0.06
    ylko
    -0.06
    POSITIVE LOGITS
    face
    0.09
    cast
    0.08
    ahead
    0.08
    å¼ı
    0.07
    casting
    0.07
    casts
    0.07
    peat
    0.06
    иÑģÑĤ
    0.06
    EXIT
    0.06
    idl
    0.06
    Activations Density 0.019%

    No Known Activations