© 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. 61146
    Prev
    Next
    INDEX
    Explanations

    physical actions or movements described 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
    776
    -0.07
    iode
    -0.06
    iku
    -0.06
    -org
    -0.06
    ichel
    -0.06
    ¶
    -0.06
     vir
    -0.06
     خص
    -0.06
     field
    -0.06
     khắc
    -0.06
    POSITIVE LOGITS
    eya
    0.09
    ÑĸйÑģ
    0.07
     Propel
    0.07
    autoplay
    0.07
    runner
    0.07
     todd
    0.07
    樹
    0.07
    rement
    0.07
    -floor
    0.07
    inning
    0.06
    Activations Density 0.009%

    No Known Activations