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

    Neuronpedia

    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. 129645
    Prev
    Next
    INDEX
    Explanations

    mentions of specific subjects or areas of focus

    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
    unday
    -0.08
    avin
    -0.08
    icer
    -0.07
    anut
    -0.07
    моÑģ
    -0.07
    retty
    -0.07
    ảo
    -0.07
    urre
    -0.07
    hare
    -0.07
    .sessions
    -0.07
    POSITIVE LOGITS
    709
    0.07
     volum
    0.07
     gene
    0.06
     elsewhere
    0.06
    _IRQ
    0.06
    gene
    0.06
     tot
    0.06
    /../
    0.06
    .Generated
    0.06
     Unicode
    0.06
    Activations Density 0.000%

    No Known Activations