© 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. 42141
    Prev
    Next
    INDEX
    Explanations

    therefore inability to answer

    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
    eli
    -0.08
     pÅĻitom
    -0.08
     marginal
    -0.08
    ï¼Ń
    -0.08
    ERVE
    -0.08
    allel
    -0.08
    è¿ĺæľī
    -0.08
    zel
    -0.08
     yem
    -0.08
    .ci
    -0.08
    POSITIVE LOGITS
    åıªèĥ½
    0.16
     cannot
    0.16
    æĹłæ³ķ
    0.16
     nor
    0.16
     therefore
    0.15
     sorry
    0.15
     Nor
    0.14
     any
    0.14
     Instead
    0.13
    cannot
    0.13
    Activations Density 0.070%

    No Known Activations