© 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. 121579
    Prev
    Next
    INDEX
    Explanations

    topics related to academic and professional disciplines

    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
    arding
    -0.07
    atto
    -0.07
    \grid
    -0.07
    aised
    -0.07
    Wunused
    -0.07
    etine
    -0.07
    iden
    -0.06
    Ľi
    -0.06
    hausen
    -0.06
    /fontawesome
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.07
     Dak
    0.06
    oran
    0.06
     fit
    0.06
     widest
    0.06
    λικ
    0.06
     svob
    0.05
    _placement
    0.05
     deals
    0.05
     ragaz
    0.05
    Activations Density 0.015%

    No Known Activations