© 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. 57212
    Prev
    Next
    INDEX
    Explanations

    répond Ãł une demande

    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
     Charter
    -0.09
    .rev
    -0.09
     Gow
    -0.09
     evasion
    -0.09
    ippi
    -0.09
     vite
    -0.08
     ëħĦëıĦë³Ħ
    -0.08
    ify
    -0.08
    deg
    -0.08
     Humb
    -0.08
    POSITIVE LOGITS
     returned
    0.10
    vide
    0.09
     McD
    0.09
    åij¼
    0.09
     Franken
    0.09
     vide
    0.09
    odata
    0.09
    ÅĻet
    0.08
     memor
    0.08
     calling
    0.08
    Activations Density 0.086%

    No Known Activations