© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 30999
    Prev
    Next
    INDEX
    Explanations

    quotes or specific words

    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
     nuest
    -0.09
     -*-č\n
    -0.08
    ldkf
    -0.08
    .TabIndex
    -0.08
     ëĦ¤ìĿ´íĬ¸
    -0.07
     FetchType
    -0.07
     migrationBuilder
    -0.07
    eca
    -0.07
    zÅij
    -0.07
    zt
    -0.07
    POSITIVE LOGITS
     \`
    0.09
    linky
    0.09
     #
    0.08
    Unnamed
    0.08
     multim
    0.08
     afore
    0.08
    oksen
    0.08
    ãģĹãĤĩ
    0.08
     â
    0.08
    benh
    0.08
    Activations Density 0.034%

    No Known Activations