© 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. 58640
    Prev
    Next
    INDEX
    Explanations

    purification

    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
    nes
    -0.11
    à¥ģरस
    -0.09
    rene
    -0.09
    ourn
    -0.09
    acd
    -0.09
    atürk
    -0.09
     Mich
    -0.09
    okit
    -0.08
    chan
    -0.08
    uibModal
    -0.08
    POSITIVE LOGITS
    pur
    0.13
     Pur
    0.13
     pur
    0.13
    bred
    0.12
    se
    0.11
    ication
    0.11
    ishment
    0.11
    ately
    0.10
    ishing
    0.10
    fection
    0.10
    Activations Density 0.008%

    No Known Activations