© 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. 15-LLAMASCOPE-RES-131K
    11. 90462
    Prev
    Next
    INDEX
    Explanations

    coding patterns and error handling in programming contexts

    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
    .synthetic
    -0.07
    olin
    -0.06
    _pago
    -0.06
     Wagner
    -0.06
    âĢij
    -0.06
    ]={↵
    -0.06
     automatic
    -0.06
    uen
    -0.06
    óln
    -0.06
    ulin
    -0.05
    POSITIVE LOGITS
    idor
    0.07
    idar
    0.07
    ipt
    0.07
    दर
    0.06
    ãĤ¿ãĤ¤
    0.06
    [--
    0.06
    nech
    0.06
    [js
    0.06
    .mk
    0.06
    crete
    0.06
    Activations Density 0.057%

    No Known Activations