© 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 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. 15-LLAMASCOPE-RES-131K
    11. 88648
    Prev
    Next
    INDEX
    Explanations

    technical terms and processes related to winemaking

    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
    abwe
    -0.07
    enk
    -0.06
    cripts
    -0.06
    iten
    -0.06
    _toggle
    -0.06
    ONO
    -0.06
    onga
    -0.06
    .bi
    -0.06
    CHA
    -0.05
     Toggle
    -0.05
    POSITIVE LOGITS
    aller
    0.07
     accuracy
    0.07
    accuracy
    0.07
     Accuracy
    0.07
     Vern
    0.06
    valuator
    0.06
     markings
    0.06
    &q
    0.06
    [](
    0.06
     accurate
    0.06
    Activations Density 0.010%

    No Known Activations