© 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. 49421
    Prev
    Next
    INDEX
    Explanations

    list separators and conjunctions

    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
     ragaz
    -0.09
    łéĻ¤
    -0.08
    gnore
    -0.08
     -*-č\n
    -0.08
    edenÃŃ
    -0.08
    ķãĤĵ
    -0.08
    avras
    -0.07
    Å¡ker
    -0.07
    biên
    -0.07
    ierge
    -0.07
    POSITIVE LOGITS
     etc
    0.11
    //{{
    0.10
    etc
    0.09
    /or
    0.08
    /inc
    0.08
    ,eg
    0.07
    odate
    0.07
    atory
    0.07
    acles
    0.07
     naopak
    0.07
    Activations Density 0.182%

    No Known Activations