© 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. 126805
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their arrangement in sentences

    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
    endor
    -0.06
    isa
    -0.05
     supply
    -0.05
    isia
    -0.05
    -main
    -0.05
    783
    -0.05
     perpetrated
    -0.05
    Main
    -0.05
     armor
    -0.05
    å¯Ħ
    -0.05
    POSITIVE LOGITS
    Violation
    0.10
    Exceptions
    0.09
     Exceptions
    0.08
     Viol
    0.08
     exceptions
    0.08
    PPER
    0.08
    .decorate
    0.08
     viol
    0.08
    YPE
    0.08
    gli
    0.08
    Activations Density 0.046%

    No Known Activations