© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 86264
    Prev
    Next
    INDEX
    Explanations

    references to scholarly research and its significance

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ç·ł
    -0.07
     assort
    -0.07
    ensa
    -0.07
    ÎŃν
    -0.06
    plx
    -0.06
    .cbo
    -0.06
    kov
    -0.06
    airs
    -0.06
    éĽ
    -0.06
    âĢĮسÛĮ
    -0.06
    POSITIVE LOGITS
     research
    0.07
    ernes
    0.06
     prelim
    0.06
    Keywords
    0.06
    quete
    0.06
     haus
    0.06
    çłĶ究
    0.06
    shm
    0.06
    çĶ³
    0.06
    FG
    0.06
    Activations Density 0.001%

    No Known Activations