© 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. 55909
    Prev
    Next
    INDEX
    Explanations

    the word "on" and its variations, indicating a focus on ongoing actions or conditions

    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
    abit
    -0.07
    avor
    -0.07
    zes
    -0.07
     kostenlose
    -0.07
    zeug
    -0.07
    WH
    -0.07
    ắt
    -0.07
     billeder
    -0.07
    isper
    -0.07
     QLatin
    -0.07
    POSITIVE LOGITS
     whether
    0.16
     how
    0.13
     Whether
    0.10
    whether
    0.10
     what
    0.09
    Whether
    0.09
    æĺ¯åIJ¦
    0.09
     WHETHER
    0.09
    how
    0.09
     where
    0.07
    Activations Density 0.012%

    No Known Activations