© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 82760
    Prev
    Next
    INDEX
    Explanations

    logging and alerting statements in code

    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
    adal
    -0.07
    elp
    -0.07
    ymm
    -0.06
    éϽ
    -0.06
     ============================================================================↵
    -0.06
    è¼Ŀ
    -0.06
    éĺ³
    -0.06
    oucher
    -0.06
    amber
    -0.06
     
    -0.06
    POSITIVE LOGITS
    olla
    0.07
    /WebAPI
    0.07
    æĽ°
    0.07
    .CG
    0.06
    _Printf
    0.06
    erli
    0.06
    lamaz
    0.06
    ibraltar
    0.06
    ĵn
    0.06
    aris
    0.06
    Activations Density 0.020%

    No Known Activations