© 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. 70146
    Prev
    Next
    INDEX
    Explanations

    culinary terms 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
     Chain
    -0.08
    Chain
    -0.07
     chain
    -0.07
     brass
    -0.06
    rase
    -0.06
     Crown
    -0.06
     Castle
    -0.06
    oldt
    -0.06
    -chain
    -0.06
    _chain
    -0.06
    POSITIVE LOGITS
    -scalable
    0.07
    /dc
    0.07
     Charleston
    0.07
    anye
    0.06
     ride
    0.06
     Benghazi
    0.06
     Ballet
    0.06
    _DC
    0.06
     rides
    0.06
    -src
    0.06
    Activations Density 0.002%

    No Known Activations