© 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. 89858
    Prev
    Next
    INDEX
    Explanations

    expressions of self-identity and personal pride

    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
    ilogy
    -0.07
    /std
    -0.07
    sect
    -0.07
    è¿İ
    -0.06
    aters
    -0.06
     hatta
    -0.06
    actly
    -0.06
    qv
    -0.06
     misd
    -0.06
     CONSEQUENTIAL
    -0.06
    POSITIVE LOGITS
    azu
    0.07
    UNUSED
    0.06
    аÑĤо
    0.06
    audi
    0.06
     writing
    0.06
    ãģħ
    0.06
    azar
    0.06
    229
    0.06
    ạn
    0.06
    icmp
    0.06
    Activations Density 0.030%

    No Known Activations