© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 127326
    Prev
    Next
    INDEX
    Explanations

    the word "why" indicating inquiries or reasons behind actions or situations

    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
    ikan
    -0.07
    ivot
    -0.07
    ë°Ģ
    -0.07
     Sheridan
    -0.06
    ovu
    -0.06
    ivec
    -0.06
    Ä«
    -0.06
    ıf
    -0.06
    /or
    -0.06
    POSITIVE LOGITS
    keh
    0.08
    -called
    0.07
    ä¹İ
    0.07
    kdir
    0.06
     we
    0.06
    -ÑĤо
    0.06
    riad
    0.06
    Ю
    0.06
     inan
    0.06
    oz
    0.06
    Activations Density 0.008%

    No Known Activations