© 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. 121421
    Prev
    Next
    INDEX
    Explanations

    verbs and phrases related to guidance or direction

    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
    avana
    -0.06
    خت
    -0.06
    -ни
    -0.06
    (ERR
    -0.06
    ewise
    -0.06
    oph
    -0.06
    .Îł
    -0.06
     upstream
    -0.06
    sek
    -0.06
     timespec
    -0.06
    POSITIVE LOGITS
    marshall
    0.08
     into
    0.07
    625
    0.07
    åı¯æĺ¯
    0.06
     naar
    0.06
    zza
    0.06
    stice
    0.06
    unning
    0.06
    gers
    0.06
     onto
    0.06
    Activations Density 0.006%

    No Known Activations