© 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. 83075
    Prev
    Next
    INDEX
    Explanations

    instances of significant actions or changes made in various contexts

    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
    okit
    -0.07
    amoto
    -0.07
     sometimes
    -0.07
     various
    -0.07
     etc
    -0.07
    olumn
    -0.07
     eventually
    -0.07
    oretical
    -0.07
    ivant
    -0.06
     ultimately
    -0.06
    POSITIVE LOGITS
     ë°Ķë¡ľ
    0.10
     when
    0.08
    ünd
    0.07
     called
    0.07
    çļĦæĺ¯
    0.07
    untu
    0.07
     viz
    0.06
    ones
    0.06
     lorsque
    0.06
    боÑĢ
    0.06
    Activations Density 0.033%

    No Known Activations