© 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. 96001
    Prev
    Next
    INDEX
    Explanations

    references to templates and their attributes or functions

    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
    opa
    -0.06
    äll
    -0.06
    anford
    -0.06
    rief
    -0.06
    uhe
    -0.05
     fuzz
    -0.05
    bove
    -0.05
     diff
    -0.05
    endon
    -0.05
    .system
    -0.05
    POSITIVE LOGITS
    _exempt
    0.06
    bish
    0.06
    bere
    0.06
    flake
    0.06
    698
    0.06
    вÑĥ
    0.06
    vens
    0.06
     Pink
    0.06
     Kushner
    0.06
    _COMMIT
    0.06
    Activations Density 0.000%

    No Known Activations