© 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. 36566
    Prev
    Next
    INDEX
    Explanations

    provided to me

    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
     senin
    -0.11
    arResult
    -0.10
    irc
    -0.09
    ï¼ľ
    -0.08
    _LP
    -0.08
     Hüs
    -0.08
    edic
    -0.08
     isten
    -0.08
    ÐIJÑĢÑħÑĸв
    -0.08
     jego
    -0.08
    POSITIVE LOGITS
     him
    0.41
     them
    0.34
     us
    0.33
     me
    0.29
     lui
    0.24
     него
    0.23
    him
    0.22
     ihn
    0.22
    them
    0.22
     mình
    0.21
    Activations Density 0.119%

    No Known Activations