© 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. 76323
    Prev
    Next
    INDEX
    Explanations

    terms related to convergence 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
    bons
    -0.07
    ç±į
    -0.07
    ified
    -0.07
    mul
    -0.07
    istry
    -0.07
    sko
    -0.07
    ume
    -0.07
    ç´ł
    -0.06
    mono
    -0.06
    rolled
    -0.06
    POSITIVE LOGITS
    /div
    0.09
    ingly
    0.08
    ãģ«åIJij
    0.07
    ault
    0.07
     thrilling
    0.06
    antly
    0.06
    icut
    0.06
     ngại
    0.06
    ently
    0.06
    ¢åįķ
    0.06
    Activations Density 0.012%

    No Known Activations