© 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. 123613
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names, particularly of people and organizations

    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
     baiser
    -0.07
    ££
    -0.06
    lace
    -0.06
    Shock
    -0.06
    ses
    -0.06
    REAM
    -0.06
    wan
    -0.06
    /process
    -0.06
    ji
    -0.06
    åĨ
    -0.06
    POSITIVE LOGITS
     earlier
    0.08
    ONTAL
    0.07
    Meanwhile
    0.07
     Else
    0.07
     Meanwhile
    0.07
    .GetKey
    0.07
     last
    0.07
     Thursday
    0.07
    ¯u
    0.07
    лем
    0.07
    Activations Density 0.004%

    No Known Activations