© 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. 3179
    Prev
    Next
    INDEX
    Explanations

    conversational phrases expressing doubt or contradiction

    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
     just
    -0.07
    ç«Ł
    -0.07
    oren
    -0.07
    ille
    -0.07
     either
    -0.07
     although
    -0.06
     altogether
    -0.06
     rather
    -0.06
    implode
    -0.06
     even
    -0.06
    POSITIVE LOGITS
     occasionally
    0.09
     SOME
    0.08
     конеÑĩно
    0.08
    ursor
    0.07
    äºĽ
    0.07
     иногда
    0.07
     maybe
    0.07
    maybe
    0.07
    æľīäºĽ
    0.07
    some
    0.07
    Activations Density 0.047%

    No Known Activations