© 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. 117481
    Prev
    Next
    INDEX
    Explanations

    cooking-related instructions and actions

    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
    ACLE
    -0.07
    icros
    -0.06
    .setGeometry
    -0.06
    Inflater
    -0.06
     tel
    -0.06
     Mans
    -0.06
     Tel
    -0.06
    beeld
    -0.06
    tel
    -0.06
    æİĴ
    -0.06
    POSITIVE LOGITS
    Sharper
    0.08
     brittle
    0.07
    OCUMENT
    0.07
    ĶåĽŀ
    0.07
     storage
    0.07
     thÆ°á»Łng
    0.07
    STORE
    0.06
    omens
    0.06
    USES
    0.06
     storing
    0.06
    Activations Density 0.010%

    No Known Activations