© 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. 28253
    Prev
    Next
    INDEX
    Explanations

    please thank you

    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
    àµįà´
    -0.16
    à±
    -0.16
    à§ĩ
    -0.15
    à¯ģ
    -0.13
    াà¦
    -0.13
    à«
    -0.12
    ிà®
    -0.12
    à§įà¦
    -0.11
    धर
    -0.11
    ¾
    -0.11
    POSITIVE LOGITS
    র
    0.13
     Vul
    0.11
    yr
    0.09
    Ø¡
    0.09
    yll
    0.09
     Martial
    0.09
    FTA
    0.08
    zen
    0.08
     Vib
    0.08
    à¸Ľà¸£à¸°à¸¡à¸²à¸ĵ
    0.08
    Activations Density 0.044%

    No Known Activations