© 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. 9-LLAMASCOPE-RES-131K
    6. 95516
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "rewrite" and its related variations in the context of configuration files

    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
    eric
    -0.07
    ant
    -0.07
    ister
    -0.06
    asc
    -0.06
    assen
    -0.06
    adow
    -0.06
    ochen
    -0.06
    à¹Ĩ
    -0.06
    OP
    -0.06
    pler
    -0.06
    POSITIVE LOGITS
    -Identifier
    0.07
    RenderingContext
    0.07
    عاÙĨ
    0.06
     Uz
    0.06
    ushman
    0.06
    /catalog
    0.06
    ÑĮе
    0.06
    inç
    0.06
    sız
    0.06
    åĽ£
    0.06
    Activations Density 0.001%

    No Known Activations