© 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. 82616
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate contradiction or contrast in a narrative

    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
    ropol
    -0.07
    arella
    -0.07
    ä¸įå¾Ĺ
    -0.06
    opol
    -0.06
     Succ
    -0.06
    æĮ¯ãĤĬ
    -0.06
    amate
    -0.06
    _TOO
    -0.06
    ahat
    -0.06
    owie
    -0.06
    POSITIVE LOGITS
     otherwise
    0.08
     plenty
    0.08
     perfectly
    0.07
     rõ
    0.07
     promise
    0.07
     clearly
    0.07
     capable
    0.07
     supposedly
    0.07
    ColumnType
    0.07
     jinak
    0.06
    Activations Density 0.055%

    No Known Activations