© 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. 15-LLAMASCOPE-RES-131K
    11. 86189
    Prev
    Next
    INDEX
    Explanations

    references to items or options listed below in a text

    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
    ist
    -0.07
    ison
    -0.06
    ib
    -0.06
    /cpu
    -0.06
    odes
    -0.06
    thon
    -0.06
     Mutable
    -0.06
    hol
    -0.06
    óc
    -0.06
     Demir
    -0.06
    POSITIVE LOGITS
    halb
    0.07
    ghi
    0.07
    otope
    0.07
    otch
    0.07
    neath
    0.07
    .scalablytyped
    0.07
    .Dom
    0.07
    pread
    0.07
    ANGER
    0.07
    asio
    0.07
    Activations Density 0.012%

    No Known Activations