© 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. 41871
    Prev
    Next
    INDEX
    Explanations

    charge and forms

    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
     charges
    -0.10
    chie
    -0.10
     charging
    -0.10
    /change
    -0.10
    lish
    -0.10
     Eins
    -0.09
    eh
    -0.09
    _charge
    -0.09
    ilogue
    -0.09
     chances
    -0.08
    POSITIVE LOGITS
    able
    0.16
    back
    0.12
    ierten
    0.11
    reuse
    0.11
     batteries
    0.11
     Nach
    0.11
    пион
    0.10
    -sheet
    0.10
    backs
    0.10
    JNI
    0.10
    Activations Density 0.030%

    No Known Activations