© 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. 2774
    Prev
    Next
    INDEX
    Explanations

    to try, enter, or excel

    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
     reloc
    -0.11
     relocated
    -0.10
     Alter
    -0.09
    æ¶Ī
    -0.09
     redistributed
    -0.09
     withdrawing
    -0.09
    uche
    -0.08
    ozo
    -0.08
    uther
    -0.08
    oton
    -0.08
    POSITIVE LOGITS
     switch
    0.51
     transition
    0.47
    switch
    0.40
     Switch
    0.38
     switched
    0.37
     switching
    0.37
    transition
    0.36
     move
    0.36
    Switch
    0.36
     пеÑĢеÑħод
    0.35
    Activations Density 0.153%

    No Known Activations