© 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. 9-LLAMASCOPE-RES-131K
    11. 99197
    Prev
    Next
    INDEX
    Explanations

    web URLs

    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
    a
    -0.06
    i
    -0.06
     to
    -0.06
    -0.06
     by
    -0.06
     only
    -0.06
     hood
    -0.06
    el
    -0.06
     with
    -0.06
     because
    -0.06
    POSITIVE LOGITS
    _TAC
    0.09
    .AnchorStyles
    0.09
    anky
    0.09
    ubbo
    0.08
    PRESS
    0.08
    ££
    0.08
    æķ¦
    0.08
    YPRE
    0.08
    KeyValue
    0.08
    kses
    0.08
    Activations Density 0.008%

    No Known Activations