© 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. 20555
    Prev
    Next
    INDEX
    Explanations

    societal factors and differences

    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
     Wend
    -0.11
     subjective
    -0.10
     Fritz
    -0.09
     scenario
    -0.09
     viv
    -0.09
     Mell
    -0.09
    /*č\n
    -0.08
     fortunate
    -0.08
     discrepancy
    -0.08
    shal
    -0.08
    POSITIVE LOGITS
     studies
    0.15
     research
    0.12
    aver
    0.12
     Studies
    0.12
     differences
    0.11
    çĶ·
    0.11
    ãĤ£
    0.11
     data
    0.11
     Race
    0.11
     race
    0.11
    Activations Density 0.107%

    No Known Activations