© 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. 104956
    Prev
    Next
    INDEX
    Explanations

    instructions related to cooking processes and timings

    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
     Schwartz
    -0.06
    straight
    -0.06
    AYER
    -0.06
    yst
    -0.06
    fty
    -0.06
    nga
    -0.06
     sez
    -0.06
    ette
    -0.06
    werk
    -0.05
     Ped
    -0.05
    POSITIVE LOGITS
     another
    0.10
     further
    0.10
     thêm
    0.09
     weitere
    0.09
    继ç»Ń
    0.09
     additional
    0.09
     jeszcze
    0.08
    ersen
    0.08
    another
    0.08
     again
    0.08
    Activations Density 0.018%

    No Known Activations