© 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. 3255
    Prev
    Next
    INDEX
    Explanations

    structures and formats related to ratings or scores

    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
    ascript
    -0.07
    ại
    -0.07
    /controllers
    -0.07
    erable
    -0.06
    ayne
    -0.06
    angelo
    -0.06
     wa
    -0.06
    pons
    -0.06
    iams
    -0.06
    agnost
    -0.06
    POSITIVE LOGITS
    ếp
    0.07
    GV
    0.06
    _MAX
    0.06
     Bauer
    0.06
    l
    0.06
    MAX
    0.06
    ved
    0.06
    ÌĢ
    0.06
     semiclass
    0.06
    تس
    0.06
    Activations Density 0.003%

    No Known Activations