© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 86266
    Prev
    Next
    INDEX
    Explanations

    phrases related to food selection and health safety

    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
    locker
    -0.07
     locker
    -0.06
    925
    -0.06
    725
    -0.06
     Ñħод
    -0.06
     ÑĤи
    -0.06
    _pipe
    -0.05
    δει
    -0.05
     Compet
    -0.05
     Overse
    -0.05
    POSITIVE LOGITS
    ÅĻet
    0.08
    ocket
    0.08
     Guerr
    0.07
     Ãľl
    0.07
     criterion
    0.07
     zbo
    0.07
    okable
    0.07
    ovol
    0.07
    queda
    0.07
     createAction
    0.06
    Activations Density 0.011%

    No Known Activations