© 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. 124078
    Prev
    Next
    INDEX
    Explanations

    genetic analysis and variation in scientific studies

    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
    gni
    -0.07
    keh
    -0.07
    mtx
    -0.06
     preval
    -0.06
    ohn
    -0.06
    reply
    -0.06
    quip
    -0.06
    uluk
    -0.06
    atables
    -0.06
    hta
    -0.06
    POSITIVE LOGITS
     Intercept
    0.07
     Decom
    0.06
     model
    0.06
     contribution
    0.06
     Panel
    0.06
     Dummy
    0.06
     factors
    0.06
    ãĥ¼ãĥķ
    0.06
     models
    0.05
     Model
    0.05
    Activations Density 0.031%

    No Known Activations