© 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. 41658
    Prev
    Next
    INDEX
    Explanations

    counts and charges

    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
     felon
    -0.10
    ekim
    -0.10
     robber
    -0.10
     assail
    -0.10
     extortion
    -0.09
     crim
    -0.09
    ưỡng
    -0.09
     resent
    -0.09
     Harm
    -0.09
     bleed
    -0.09
    POSITIVE LOGITS
     charges
    0.24
     counts
    0.19
     Charges
    0.18
     charge
    0.17
    charges
    0.17
     Counts
    0.16
    arges
    0.15
     Charge
    0.14
     accessory
    0.14
    counts
    0.13
    Activations Density 0.057%

    No Known Activations