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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 90375
    Prev
    Next
    INDEX
    Explanations

    content related to structured data or coding frameworks

    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
     Gins
    -0.07
    olini
    -0.07
    ucher
    -0.06
    елÑĮно
    -0.06
    bor
    -0.06
    arbon
    -0.06
    wat
    -0.06
    ürn
    -0.06
    веÑī
    -0.06
    zept
    -0.06
    POSITIVE LOGITS
    ccak
    0.07
    lier
    0.07
    338
    0.07
    ipse
    0.06
    otomy
    0.06
    ä½
    0.06
    ourg
    0.06
    ries
    0.06
     NONINFRINGEMENT
    0.06
     Fritz
    0.06
    Activations Density 0.000%

    No Known Activations