© 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. 118613
    Prev
    Next
    INDEX
    Explanations

    mentions of the letter 'K' or variations thereof

    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
    à¤Ī
    -0.09
    ÑĢÑĸм
    -0.09
    اÙĨ
    -0.08
    ร
    -0.08
    оÑĢ
    -0.08
    ÏĮ
    -0.08
    pery
    -0.07
    ÎijÎĻ
    -0.07
    ro
    -0.07
    ÑĥÑĢ
    -0.07
    POSITIVE LOGITS
    ean
    0.08
    ac
    0.08
    ev
    0.07
    ip
    0.07
    F
    0.07
    vant
    0.07
    I
    0.07
    ne
    0.07
    oning
    0.07
    U
    0.07
    Activations Density 0.128%

    No Known Activations