Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 29249
    Prev
    Next
    INDEX
    Explanations

    code snippets related to programming practices or technical configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code implementation solutions showing exact syntax for solving programming problems, typically following a question about how to implement a specific technical feature.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    elda
    -0.07
    riangle
    -0.07
    gage
    -0.06
     Forrest
    -0.06
    angelo
    -0.06
    izacao
    -0.06
    ingles
    -0.06
     ofs
    -0.06
    arring
    -0.06
     Hansen
    -0.06
    POSITIVE LOGITS
    hope
    0.08
     exemp
    0.07
    ÑģÑĤÑĢÑĥк
    0.07
    CppType
    0.07
    udo
    0.07
    Cause
    0.07
     exemple
    0.06
     try
    0.06
     hope
    0.06
    steller
    0.06
    Activations Density 0.013%

    No Known Activations