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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 88670
    Prev
    Next
    INDEX
    Explanations

    expressions of curiosity or questioning

    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
    alin
    -0.07
    omer
    -0.06
    arn
    -0.06
    ea
    -0.06
    Bes
    -0.06
    aku
    -0.06
    alink
    -0.06
    ritch
    -0.06
    duk
    -0.06
     eiusmod
    -0.06
    POSITIVE LOGITS
     why
    0.16
    why
    0.13
     Why
    0.12
    为ä»Ģä¹Ī
    0.11
    Why
    0.10
     pourquoi
    0.09
     WHY
    0.09
     how
    0.08
     whether
    0.08
    "Why
    0.08
    Activations Density 0.015%

    No Known Activations