© 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. 59393
    Prev
    Next
    INDEX
    Explanations

    self, yourself, you

    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
     Horton
    -0.09
    ddy
    -0.09
    891
    -0.09
     Et
    -0.09
     بÙĪابة
    -0.08
     Boyle
    -0.08
    ached
    -0.08
    zu
    -0.08
    .ret
    -0.08
    eniable
    -0.08
    POSITIVE LOGITS
    .PerformLayout
    0.11
    (fullfile
    0.10
    ATUS
    0.09
    ankan
    0.09
    663
    0.09
    âij¡
    0.08
    illac
    0.08
     Sokol
    0.08
    utow
    0.08
    MenuStrip
    0.08
    Activations Density 0.114%

    No Known Activations