© 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. 28349
    Prev
    Next
    INDEX
    Explanations

    å°ıæĺİ / å°ıåı·

    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
    èĥİ
    -0.11
    asl
    -0.10
    екÑĤоÑĢ
    -0.09
    uben
    -0.09
     McCl
    -0.09
    adh
    -0.09
    å©Ĩ
    -0.09
    iers
    -0.08
    éijij
    -0.08
     Vale
    -0.08
    POSITIVE LOGITS
     gá»įn
    0.12
    -scale
    0.12
    äºİ
    0.12
    /tiny
    0.12
    æĸ¼
    0.11
    talk
    0.11
    VOICE
    0.10
    atur
    0.10
     fry
    0.10
    .sav
    0.10
    Activations Density 0.024%

    No Known Activations