© 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. 13943
    Prev
    Next
    INDEX
    Explanations

    ol, li, table, ui tags

    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
     blush
    -0.10
     Griff
    -0.10
    ntag
    -0.09
     Nico
    -0.09
     Murdoch
    -0.09
     Fortress
    -0.08
     Pap
    -0.08
     Trent
    -0.08
    adx
    -0.08
     ë¶Ħë¥ĺ
    -0.08
    POSITIVE LOGITS
     style
    0.10
    िवर
    0.09
     reversed
    0.09
    çħ§
    0.09
    ¶Į
    0.09
    IVER
    0.09
    /li
    0.09
     start
    0.08
    li
    0.08
     defaultstate
    0.08
    Activations Density 0.009%

    No Known Activations