© 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. 21112
    Prev
    Next
    INDEX
    Explanations

    deciding to act

    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
    æī¾åĪ°
    -0.13
     finden
    -0.11
    è½
    -0.09
     Tun
    -0.09
    ugu
    -0.09
     tendency
    -0.09
     Rif
    -0.09
    izo
    -0.09
    rin
    -0.09
     find
    -0.09
    POSITIVE LOGITS
     pursue
    0.15
     fore
    0.13
     Purs
    0.12
     pursued
    0.12
     invest
    0.11
     pursuing
    0.11
     opt
    0.11
    /not
    0.11
     accept
    0.10
     Invest
    0.10
    Activations Density 0.070%

    No Known Activations