© 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. 5768
    Prev
    Next
    INDEX
    Explanations

    numerical data related to performance metrics

    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
    uff
    -0.06
    arus
    -0.06
    zza
    -0.06
    èĪ
    -0.06
    ager
    -0.06
     ull
    -0.06
    ãĤıãģļ
    -0.06
     ”
    -0.06
     ziy
    -0.06
    /feed
    -0.05
    POSITIVE LOGITS
    uada
    0.08
    ughs
    0.07
    cad
    0.07
    erson
    0.07
    .FC
    0.07
    418
    0.06
    isbury
    0.06
    pretty
    0.06
    venir
    0.06
    utut
    0.06
    Activations Density 0.197%

    No Known Activations