© 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. 76920
    Prev
    Next
    INDEX
    Explanations

    locational phrases indicating various points of intersection or meeting

    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
     acomp
    -0.08
    ients
    -0.07
     mise
    -0.06
    itamin
    -0.06
    975
    -0.06
     scene
    -0.06
    :\"
    -0.06
     bs
    -0.06
    935
    -0.06
    angl
    -0.06
    POSITIVE LOGITS
    ouncil
    0.07
    inia
    0.07
    _least
    0.06
    vature
    0.06
    abin
    0.06
    ushman
    0.06
    PIP
    0.06
     æĦĽ
    0.06
    imiter
    0.06
    orc
    0.06
    Activations Density 0.018%

    No Known Activations