© 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. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 53921
    Prev
    Next
    INDEX
    Explanations

    that is executed or called

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agna
    -0.10
    ï¾ij
    -0.09
     Reb
    -0.09
     Schiff
    -0.08
     iT
    -0.08
    341
    -0.08
     Emer
    -0.08
    odes
    -0.08
    meld
    -0.08
    Ĥ¬
    -0.08
    POSITIVE LOGITS
     executed
    0.16
     fired
    0.15
     called
    0.14
     Called
    0.13
    _called
    0.13
     fires
    0.13
     Äijược
    0.12
    called
    0.12
     Fired
    0.12
     será
    0.12
    Activations Density 0.037%

    No Known Activations