© 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. 93710
    Prev
    Next
    INDEX
    Explanations

    references to the balance between comedic and dramatic roles in acting

    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
    endon
    -0.06
    achelor
    -0.05
    lá
    -0.05
     Kirby
    -0.05
    ENTS
    -0.05
    è¾ĵ
    -0.05
    erculosis
    -0.05
     intended
    -0.05
     actually
    -0.05
    KeyId
    -0.05
    POSITIVE LOGITS
     projects
    0.08
    projects
    0.07
    Projects
    0.07
     Projects
    0.07
    ãĥĮ
    0.07
    ावन
    0.07
    ypes
    0.07
    à¸Ĺย
    0.07
     ç¯
    0.07
     opportunities
    0.07
    Activations Density 0.017%

    No Known Activations