© 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. 82795
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'k' in various 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
    e
    -0.10
    ynet
    -0.07
    i
    -0.07
    y
    -0.07
     latter
    -0.07
     Welt
    -0.06
    rub
    -0.06
    atinum
    -0.06
    enstein
    -0.06
    onu
    -0.06
    POSITIVE LOGITS
    ths
    0.08
    ph
    0.07
    -REAL
    0.07
    以ä¸Ĭ
    0.07
    hões
    0.07
    à¹ģรà¸ģ
    0.07
    uforia
    0.06
    orum
    0.06
    ittest
    0.06
    aret
    0.06
    Activations Density 0.010%

    No Known Activations