© 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 EvalsExportsinterp-engineNEWAPI 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. 93292
    Prev
    Next
    INDEX
    Explanations

    questions and expressions of uncertainty regarding motives and reasons

    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
    ibern
    -0.06
    gon
    -0.06
    ãĤµãĤ¤
    -0.06
    amework
    -0.06
    ãģ¡ãģ¯
    -0.06
    toi
    -0.06
     Creatures
    -0.06
    inition
    -0.06
    вÑĸ
    -0.06
    ¿ÃĤ
    -0.06
    POSITIVE LOGITS
     suddenly
    0.14
     sudden
    0.12
     Suddenly
    0.10
     abruptly
    0.09
    uddenly
    0.08
    udden
    0.08
    Suddenly
    0.08
    çªģçĦ¶
    0.08
     à¤ĩतन
    0.08
     abrupt
    0.07
    Activations Density 0.019%

    No Known Activations