© 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. 57383
    Prev
    Next
    INDEX
    Explanations

    saying something

    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
    ones
    -0.11
    imens
    -0.09
     nowhere
    -0.09
    itos
    -0.08
    asc
    -0.08
     Zus
    -0.08
    umont
    -0.08
    à¹Ħหà¸Ļ
    -0.08
     Ones
    -0.08
     Bent
    -0.08
    POSITIVE LOGITS
     something
    0.84
    something
    0.67
     Something
    0.63
    Something
    0.60
    omething
    0.59
     etwas
    0.51
     iets
    0.50
     nÄĽco
    0.47
     algo
    0.43
     anything
    0.37
    Activations Density 0.238%

    No Known Activations