© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 128438
    Prev
    Next
    INDEX
    Explanations

    cooking techniques and instructions

    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
     Ziel
    -0.06
    /from
    -0.06
     Chase
    -0.06
     whom
    -0.06
    anje
    -0.06
    anova
    -0.06
    inka
    -0.06
     dik
    -0.06
    udies
    -0.06
     Partial
    -0.06
    POSITIVE LOGITS
    ubu
    0.08
     Laud
    0.07
     Goth
    0.07
    leyin
    0.07
    äter
    0.07
    aterangepicker
    0.07
     ÑĢÑĥками
    0.07
    uego
    0.07
    :eq
    0.07
    EMPL
    0.06
    Activations Density 0.046%

    No Known Activations