© 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. 31581
    Prev
    Next
    INDEX
    Explanations

    references to gum-related topics

    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
    ãĥ¶
    -0.08
    VRT
    -0.07
    werp
    -0.07
    orio
    -0.06
    hydr
    -0.06
    RLF
    -0.06
    emme
    -0.06
    abwe
    -0.06
    ignum
    -0.06
    pent
    -0.06
    POSITIVE LOGITS
    éry
    0.07
    jom
    0.07
    ergy
    0.07
    iciary
    0.06
    ierge
    0.06
    .Transparent
    0.06
     Chew
    0.06
    ierrez
    0.06
    foon
    0.06
    nut
    0.06
    Activations Density 0.001%

    No Known Activations