© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 127906
    Prev
    Next
    INDEX
    Explanations

    requests for clarification or updates on data-related issues

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

    Code/programming queries or examples where the user is describing an issue, requesting help, or providing context for a technical problem. Often includes descriptions of data structures, desired functionality, or specific implementation challenges.

    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
    orce
    -0.06
     tut
    -0.06
    _factory
    -0.06
    -direct
    -0.06
     hoops
    -0.06
    efa
    -0.06
    ESCO
    -0.06
     alternate
    -0.06
    paced
    -0.06
     fine
    -0.06
    POSITIVE LOGITS
     requirement
    0.07
     ÑĥÑģл
    0.07
     requirements
    0.07
     output
    0.07
    баÑĩ
    0.06
    bjerg
    0.06
     tolerance
    0.06
     constraints
    0.06
     toler
    0.06
    ![↵
    0.06
    Activations Density 0.014%

    No Known Activations