© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 13225
    Prev
    Next
    INDEX
    Explanations

    she checking innocence

    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
    rello
    -0.09
     há»
    -0.09
    erial
    -0.09
     laz
    -0.09
    ì°°
    -0.09
     erót
    -0.09
    iez
    -0.09
    arkan
    -0.09
    CED
    -0.09
    iế
    -0.09
    POSITIVE LOGITS
     virgin
    0.15
     Innoc
    0.15
     innocence
    0.14
     touch
    0.14
     curious
    0.14
     Virgin
    0.14
     innoc
    0.14
     innocent
    0.13
     bold
    0.13
     curiosity
    0.13
    Activations Density 0.044%

    No Known Activations