© 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. 40232
    Prev
    Next
    INDEX
    Explanations

    references to web application framework functions and methods

    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
    ilde
    -0.07
    adesh
    -0.07
    947
    -0.06
    icket
    -0.06
    ynch
    -0.06
    ¼åIJĪ
    -0.06
    URNS
    -0.06
    .onViewCreated
    -0.06
    adiens
    -0.06
    022
    -0.06
    POSITIVE LOGITS
    ervo
    0.08
    ãĤĵãģ©
    0.07
    .extensions
    0.07
    krom
    0.07
    cov
    0.07
    ubu
    0.06
     Hera
    0.06
    _EXTENDED
    0.06
    ovnÃŃ
    0.06
     Latter
    0.06
    Activations Density 0.030%

    No Known Activations