© 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. 71662
    Prev
    Next
    INDEX
    Explanations

    mentions of Google and related terms

    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
    steller
    -0.08
    ño
    -0.07
    ileo
    -0.06
    icari
    -0.06
    /ion
    -0.06
    undle
    -0.06
    holders
    -0.06
    idders
    -0.06
    ichtig
    -0.06
     pady
    -0.06
    POSITIVE LOGITS
    ernet
    0.08
    les
    0.08
    enda
    0.07
    redi
    0.07
    ther
    0.07
    soever
    0.07
    YM
    0.06
    .Func
    0.06
    æĽ
    0.06
     Grace
    0.06
    Activations Density 0.001%

    No Known Activations