© 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. 41764
    Prev
    Next
    INDEX
    Explanations

    physical or special

    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
    _cpus
    -0.09
    ãĢijãĢIJ
    -0.09
    ยะ
    -0.08
    _gb
    -0.08
     getItemCount
    -0.08
    BN
    -0.07
     Bever
    -0.07
    ialis
    -0.07
    _PROC
    -0.07
     recharge
    -0.07
    POSITIVE LOGITS
     physical
    0.81
    physical
    0.67
     Physical
    0.64
    Physical
    0.61
    çī©çIJĨ
    0.51
    _physical
    0.49
     fÃŃs
    0.47
     ÑĦиз
    0.47
     physically
    0.44
     fizik
    0.43
    Activations Density 0.315%

    No Known Activations