© 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. 27099
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "apply to" in varying 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
    ates
    -0.07
    kola
    -0.07
    æĽ
    -0.06
     nowhere
    -0.06
    ç¢
    -0.06
    .operations
    -0.06
    ÄĻ
    -0.06
    akes
    -0.06
     tay
    -0.06
    /tiny
    -0.06
    POSITIVE LOGITS
    386
    0.06
     situations
    0.06
    ichick
    0.06
    328
    0.06
    endra
    0.06
    تا
    0.06
    ancel
    0.06
    ffi
    0.06
     Giuliani
    0.06
    953
    0.06
    Activations Density 0.016%

    No Known Activations