© 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. 89979
    Prev
    Next
    INDEX
    Explanations

    exclamatory punctuation and expressions of strong emotion

    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
    Xem
    -0.08
    ese
    -0.07
    ula
    -0.07
    itz
    -0.07
    ism
    -0.06
    nte
    -0.06
    efined
    -0.06
    esa
    -0.06
    /or
    -0.06
    PTY
    -0.06
    POSITIVE LOGITS
    [](
    0.09
    rames
    0.08
    sgi
    0.08
    !--
    0.07
    ?!
    0.07
    unct
    0.07
    resse
    0.07
     *__
    0.07
    LLLL
    0.07
    otlin
    0.07
    Activations Density 0.104%

    No Known Activations