© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 16952
    Prev
    Next
    INDEX
    Explanations

    convert/transform ... into

    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
    afort
    -0.10
    ataka
    -0.09
     persist
    -0.09
     reb
    -0.08
     McCarthy
    -0.08
    mos
    -0.08
     Gates
    -0.08
     consist
    -0.08
     vital
    -0.08
     dues
    -0.08
    POSITIVE LOGITS
     into
    0.21
     raw
    0.18
    into
    0.16
    Into
    0.15
    raw
    0.15
    _into
    0.15
     Raw
    0.15
     Into
    0.14
     ordinary
    0.14
     RAW
    0.13
    Activations Density 0.080%

    No Known Activations