© 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. 103890
    Prev
    Next
    INDEX
    Explanations

    comment and documentation syntax in programming code

    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
    ican
    -0.07
     Bros
    -0.07
     Dahl
    -0.06
     Gard
    -0.06
     nada
    -0.06
    าà¸Ń
    -0.06
    icans
    -0.06
    ovel
    -0.06
     Zust
    -0.06
     scen
    -0.06
    POSITIVE LOGITS
    _dll
    0.07
    aptors
    0.07
    ellery
    0.07
    :UI
    0.06
    KT
    0.06
     portion
    0.06
    Ī
    0.06
    ayi
    0.06
    á»Ĩ
    0.06
    OrElse
    0.06
    Activations Density 0.001%

    No Known Activations