© 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. 9-LLAMASCOPE-RES-131K
    11. 98499
    Prev
    Next
    INDEX
    Explanations

    terms related to culinary uses and cooking methods

    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
    uce
    -0.07
     compound
    -0.06
     Compound
    -0.06
    *
    -0.06
     forc
    -0.05
    compound
    -0.05
    uma
    -0.05
    283
    -0.05
    plet
    -0.05
    esar
    -0.05
    POSITIVE LOGITS
    ibur
    0.08
    afone
    0.08
    sti
    0.07
    CLUDED
    0.07
    zure
    0.07
    ẽ
    0.07
    _RENDERER
    0.07
    MOTE
    0.07
    ETCH
    0.07
    VML
    0.07
    Activations Density 0.016%

    No Known Activations