© 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. 128654
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and symbols associated with questions and lists

    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
    entai
    -0.07
    afs
    -0.07
    -mask
    -0.07
    fsp
    -0.07
    IDS
    -0.06
    _ck
    -0.06
    åѦéĻ¢
    -0.06
    ModelIndex
    -0.06
    ifter
    -0.06
    folio
    -0.06
    POSITIVE LOGITS
    867
    0.07
     ÑĤем
    0.07
     accord
    0.06
    utom
    0.06
    ellido
    0.06
     Qui
    0.06
     detail
    0.06
     Ã
    0.06
    _exceptions
    0.06
     terms
    0.06
    Activations Density 0.003%

    No Known Activations