© 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. 20259
    Prev
    Next
    INDEX
    Explanations

    iniciar dispositivo em modo de falha ou recuperação

    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
     Schn
    -0.12
    éľ
    -0.11
     reopen
    -0.10
    å¡
    -0.10
     Mystic
    -0.09
     sod
    -0.09
    inders
    -0.09
    olare
    -0.09
     Tarif
    -0.09
    awah
    -0.09
    POSITIVE LOGITS
     Safe
    0.15
    Safe
    0.14
     safe
    0.14
     repair
    0.12
     Repair
    0.12
     diagnostic
    0.12
    .safe
    0.11
     troub
    0.11
     recovery
    0.11
     tools
    0.10
    Activations Density 0.050%

    No Known Activations