© 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. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 41855
    Prev
    Next
    INDEX
    Explanations

    B: or B. followed by text

    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
     paddle
    -0.09
     ï¼¼
    -0.09
    ÂĽ
    -0.09
    >//
    -0.08
    rn
    -0.08
     tah
    -0.08
     reporting
    -0.08
    _HERSHEY
    -0.08
    ah
    -0.08
     bargain
    -0.08
    POSITIVE LOGITS
    ingen
    0.10
    foy
    0.09
    witter
    0.09
    rut
    0.09
    yles
    0.08
    éĢī
    0.08
     correct
    0.08
    aky
    0.08
    Correct
    0.08
    'gc
    0.08
    Activations Density 0.046%

    No Known Activations