© 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. 106328
    Prev
    Next
    INDEX
    Explanations

    log messages and output statements in programming 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
    IMP
    -0.07
    uo
    -0.06
    avery
    -0.06
    lej
    -0.06
    ee
    -0.06
    lé
    -0.06
    _FAULT
    -0.06
     latter
    -0.06
    itchen
    -0.06
     cust
    -0.06
    POSITIVE LOGITS
    onga
    0.08
     herk
    0.07
    /welcome
    0.07
    reative
    0.07
    REEN
    0.06
    ouden
    0.06
    íĺ¸
    0.06
    ÄĽÅĻ
    0.06
    quo
    0.06
    _PE
    0.06
    Activations Density 0.021%

    No Known Activations