© 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. 103922
    Prev
    Next
    INDEX
    Explanations

    references to automated processes and systems

    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
    .bp
    -0.07
    clamp
    -0.07
    sel
    -0.07
    /Linux
    -0.07
    /her
    -0.07
    .rpm
    -0.07
    ãĤ©
    -0.06
    _MALLOC
    -0.06
    ChangeEvent
    -0.06
    periences
    -0.06
    POSITIVE LOGITS
    /auto
    0.09
    /manual
    0.08
    aly
    0.08
     auto
    0.07
    auto
    0.07
    infer
    0.06
     Mixed
    0.06
     Auto
    0.06
    \:
    0.06
    (auto
    0.06
    Activations Density 0.010%

    No Known Activations