© 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. 31572
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to literature or notable works

    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
    lam
    -0.07
    æħ¶
    -0.07
    abyrinth
    -0.07
    arith
    -0.06
    dsp
    -0.06
    ifferent
    -0.06
    alim
    -0.06
    numer
    -0.06
    amina
    -0.06
    untas
    -0.06
    POSITIVE LOGITS
     Fab
    0.07
    fab
    0.07
    Fab
    0.07
    gate
    0.07
    .nih
    0.07
     fab
    0.06
    agy
    0.06
     guint
    0.06
    ighbor
    0.06
    irth
    0.06
    Activations Density 0.005%

    No Known Activations