© 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. 81352
    Prev
    Next
    INDEX
    Explanations

    quantitative information and statistics related to numbers

    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
    alsa
    -0.08
    aira
    -0.07
    üz
    -0.07
    ÐĿЯ
    -0.07
    olini
    -0.07
     yans
    -0.07
    -UA
    -0.07
     либо
    -0.07
    ulo
    -0.07
    uro
    -0.07
    POSITIVE LOGITS
     which
    0.09
     for
    0.08
     times
    0.08
     being
    0.08
     in
    0.08
     with
    0.07
     thereof
    0.07
     Ones
    0.07
     them
    0.07
     of
    0.07
    Activations Density 0.019%

    No Known Activations