© 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. 35656
    Prev
    Next
    INDEX
    Explanations

    permutations and combinations

    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
    enga
    -0.11
     Bil
    -0.11
    AME
    -0.10
     bil
    -0.10
     concaten
    -0.09
     rational
    -0.09
     pairwise
    -0.09
     Furious
    -0.09
    ebra
    -0.09
    imus
    -0.09
    POSITIVE LOGITS
     combinations
    0.26
    binations
    0.21
     comb
    0.21
     Combination
    0.19
     combination
    0.19
    _comb
    0.17
     perm
    0.16
    Comb
    0.16
    ç¬
    0.16
    combination
    0.16
    Activations Density 0.091%

    No Known Activations