© 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. 42617
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of individuals and organizations

    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
    tember
    -0.07
    áo
    -0.07
     pii
    -0.07
    ;charset
    -0.07
    libft
    -0.07
     æĹ
    -0.06
    ;break
    -0.06
     relat
    -0.06
     {}:
    -0.06
    lint
    -0.06
    POSITIVE LOGITS
    ↵
    0.07
    erner
    0.07
    cka
    0.06
     stead
    0.06
    .eql
    0.06
    *↵
    0.06
    ?↵
    0.06
    ï¼Ł↵
    0.06
    âĢ¦↵
    0.06
    âĺĨ
    0.06
    Activations Density 0.029%

    No Known Activations