© 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. 29886
    Prev
    Next
    INDEX
    Explanations

    perceived as offensive

    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
     absorbing
    -0.09
    ipur
    -0.08
    _hpp
    -0.08
    ccd
    -0.08
    likle
    -0.08
    -human
    -0.08
    ourke
    -0.08
    esine
    -0.08
    (COLOR
    -0.08
     Ports
    -0.08
    POSITIVE LOGITS
     reception
    0.22
     interpreted
    0.19
     Reception
    0.17
     perceived
    0.17
     interpret
    0.17
    interpreted
    0.16
     interpretation
    0.16
     offense
    0.16
     interpretations
    0.16
    interpret
    0.16
    Activations Density 0.100%

    No Known Activations