© 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. 75581
    Prev
    Next
    INDEX
    Explanations

    descriptions of unique and traditional foods

    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
    eman
    -0.07
    ugin
    -0.07
     bake
    -0.06
    ников
    -0.06
     desi
    -0.06
     freshness
    -0.06
    .tc
    -0.06
    eus
    -0.06
    exual
    -0.06
    ýš
    -0.06
    POSITIVE LOGITS
    abor
    0.08
     variations
    0.08
     popular
    0.07
    _executor
    0.07
    $MESS
    0.07
    annon
    0.07
    variation
    0.07
     variants
    0.07
    ariant
    0.07
     variant
    0.07
    Activations Density 0.042%

    No Known Activations