© 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. 60836
    Prev
    Next
    INDEX
    Explanations

    multiplication and digits

    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
    eldorf
    -0.10
    ((*
    -0.10
    /=
    -0.09
    477
    -0.09
     vess
    -0.08
    ï¼ı:
    -0.08
    anic
    -0.08
     Subtract
    -0.08
    ellung
    -0.08
    aphore
    -0.08
    POSITIVE LOGITS
     *
    0.30
     ÃĹ
    0.29
     times
    0.26
    ÃĹ
    0.23
    times
    0.21
    *
    0.19
    \t
    0.19
     *\n
    0.17
    _times
    0.17
     TIMES
    0.17
    Activations Density 0.051%

    No Known Activations