© 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. 61001
    Prev
    Next
    INDEX
    Explanations

    derogatory comments or language

    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
    .scalablytyped
    -0.11
    lef
    -0.10
    âĢIJ-
    -0.09
     Freund
    -0.09
    .mybatisplus
    -0.09
    MessageType
    -0.08
    _WP
    -0.08
     cum
    -0.08
    BUM
    -0.08
     Laurent
    -0.08
    POSITIVE LOGITS
     directed
    0.24
     towards
    0.20
     toward
    0.19
     against
    0.19
     Directed
    0.17
     about
    0.17
    Directed
    0.15
    against
    0.14
     vůÄįi
    0.14
     hacia
    0.14
    Activations Density 0.094%

    No Known Activations