© 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. 104121
    Prev
    Next
    INDEX
    Explanations

    formatted dates and versions

    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
     Fro
    -0.07
    utton
    -0.07
    udem
    -0.07
    EntryPoint
    -0.07
    odash
    -0.06
    ãĥ³ãĤ°ãĥ«
    -0.06
    ills
    -0.06
     sack
    -0.06
    .XR
    -0.06
    inem
    -0.06
    POSITIVE LOGITS
     vault
    0.07
    æĻ´
    0.07
    erk
    0.06
     Vaults
    0.06
    riel
    0.06
    ormsg
    0.06
    hair
    0.06
    ÄĽÅĻ
    0.06
    OLE
    0.06
    δε
    0.06
    Activations Density 0.008%

    No Known Activations