© 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. 42536
    Prev
    Next
    INDEX
    Explanations

    suspicious activity or suspension

    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
    eron
    -0.11
    ãģĬãĤĬ
    -0.10
    UMENT
    -0.10
     ³³ ³³
    -0.09
    AGO
    -0.09
    iten
    -0.09
    adh
    -0.09
    eras
    -0.09
    erty
    -0.09
    asc
    -0.09
    POSITIVE LOGITS
    ively
    0.14
    ibilities
    0.13
     Sus
    0.13
     disbelief
    0.12
    ibility
    0.12
    ible
    0.12
    ably
    0.12
    cies
    0.11
     Susp
    0.11
    icious
    0.11
    Activations Density 0.023%

    No Known Activations