© 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. 41715
    Prev
    Next
    INDEX
    Explanations

    cc followed by 1, 106, or ASS

    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
    ascade
    -0.12
    semb
    -0.11
    rech
    -0.11
     Vall
    -0.10
    ounter
    -0.10
    ount
    -0.10
    bff
    -0.10
    lient
    -0.09
    centage
    -0.09
    ripp
    -0.09
    POSITIVE LOGITS
    (CC
    0.14
     BY
    0.13
    /cc
    0.11
    ccc
    0.10
    iya
    0.10
    leston
    0.10
    asionally
    0.10
    agh
    0.10
    ITT
    0.10
    lesi
    0.10
    Activations Density 0.024%

    No Known Activations