© 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. 64306
    Prev
    Next
    INDEX
    Explanations

    to each other / to flirt / them jump

    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
    fra
    -0.10
     Fra
    -0.09
    ief
    -0.09
     veter
    -0.09
     explo
    -0.08
     ÙĤØ·
    -0.08
     offsetof
    -0.08
    emon
    -0.08
    aco
    -0.08
    ç½®
    -0.08
    POSITIVE LOGITS
    æŃ£åľ¨
    0.10
    à¸ģาร
    0.09
     resort
    0.09
     propensity
    0.08
    verb
    0.08
    à¸Īาà¸ģà¸ģาร
    0.08
    oda
    0.08
    iesz
    0.08
    STANCE
    0.08
     mosaic
    0.08
    Activations Density 0.248%

    No Known Activations