© 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. 37114
    Prev
    Next
    INDEX
    Explanations

    conversational roles or scientific formulas

    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
    ï¿£ï½Ģ
    -0.08
     вб
    -0.08
     Bender
    -0.08
     hik
    -0.07
    reib
    -0.07
    lauf
    -0.07
     olmasına
    -0.07
     Elm
    -0.07
    ysi
    -0.07
     Tier
    -0.07
    POSITIVE LOGITS
    ¦æĥħ
    0.10
     question
    0.09
    รà¸ģ
    0.09
     ãĥİ
    0.09
    loor
    0.09
    edenÃŃ
    0.08
    >NN
    0.08
     Blasio
    0.08
    วล
    0.08
    liest
    0.08
    Activations Density 0.272%

    No Known Activations