© 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. 17-LLAMASCOPE-RES-131K
    11. 75288
    Prev
    Next
    INDEX
    Explanations

    elements related to programming annotations and methods

    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
    inance
    -0.07
    hea
    -0.06
    cola
    -0.06
    -
    -0.06
    print
    -0.06
    723
    -0.06
    ics
    -0.06
    per
    -0.06
    į°
    -0.06
    kle
    -0.05
    POSITIVE LOGITS
    ализи
    0.07
    akedirs
    0.07
    /OR
    0.07
    egrator
    0.07
    -widgets
    0.07
    Inactive
    0.07
    лада
    0.07
     Slov
    0.06
     rám
    0.06
    itm
    0.06
    Activations Density 0.000%

    No Known Activations