© 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. 16082
    Prev
    Next
    INDEX
    Explanations

    references to communication or correspondence, particularly in the context of emails or replies

    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
    rons
    -0.07
    ron
    -0.06
    ULO
    -0.06
     Glow
    -0.06
    oli
    -0.06
    raf
    -0.06
    ARN
    -0.06
    ãĥ¼ãĥŃ
    -0.06
    arn
    -0.06
    oop
    -0.06
    POSITIVE LOGITS
    让æĪij
    0.08
    วà¸Ļ
    0.08
    iamond
    0.08
    æĤ¨çļĦ
    0.08
    Å¡ov
    0.08
    天åłĤ
    0.07
    æĭ©
    0.07
     recent
    0.07
    /comments
    0.06
     CHtml
    0.06
    Activations Density 0.030%

    No Known Activations