© 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. 17-LLAMASCOPE-RES-131K
    11. 57454
    Prev
    Next
    INDEX
    Explanations

    elements related to food preparation and recipe 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
     dishes
    -0.07
    gard
    -0.07
    pel
    -0.07
     popcorn
    -0.06
    rn
    -0.06
    otts
    -0.06
     Trail
    -0.06
    ëŀĢ
    -0.06
     Ming
    -0.06
    ott
    -0.06
    POSITIVE LOGITS
     sandwich
    0.13
     Sandwich
    0.12
     sandwiches
    0.10
     SAND
    0.09
    Sand
    0.08
     bread
    0.08
    tearDown
    0.07
     bun
    0.07
    sand
    0.07
     presses
    0.07
    Activations Density 0.239%

    No Known Activations