© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 123480
    Prev
    Next
    INDEX
    Explanations

    variable declarations in code

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    Ãł
    -0.07
    wn
    -0.07
    ie
    -0.07
    iel
    -0.07
    ault
    -0.07
    ly
    -0.06
    lm
    -0.06
    of
    -0.06
    in
    -0.06
    or
    -0.06
    POSITIVE LOGITS
     (_,
    0.09
    tual
    0.08
    quez
    0.07
    дон
    0.07
    \Migration
    0.07
    antro
    0.07
    ÄŁinden
    0.07
    ULE
    0.07
    celik
    0.07
    utomation
    0.07
    Activations Density 0.004%

    No Known Activations