© 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. 54652
    Prev
    Next
    INDEX
    Explanations

    references to types of burgers or burger-related ingredients in recipes

    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
    ofilm
    -0.08
     sieve
    -0.07
    kám
    -0.07
    eva
    -0.07
    chten
    -0.07
    acic
    -0.07
    _sid
    -0.07
     dess
    -0.07
    PEnd
    -0.07
    monds
    -0.07
    POSITIVE LOGITS
     meat
    0.09
     Burg
    0.09
     ground
    0.08
     min
    0.07
     burgers
    0.07
     Ground
    0.07
     Meat
    0.07
     sausage
    0.07
     burger
    0.07
    amburg
    0.07
    Activations Density 0.176%

    No Known Activations