© 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. 34167
    Prev
    Next
    INDEX
    Explanations

    talking about sometimes

    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
     typical
    -0.09
     toReturn
    -0.08
    889
    -0.08
     )\n\n\n\n\n\n\n\n
    -0.08
    oka
    -0.08
     Hass
    -0.08
    <br
    -0.08
    å¿ħé¡»
    -0.08
     Disp
    -0.08
     :\n\n\n\n
    -0.08
    POSITIVE LOGITS
     sometimes
    0.20
     Sometimes
    0.20
    Sometimes
    0.18
    sometimes
    0.17
     talking
    0.13
     иногда
    0.12
     Often
    0.12
     often
    0.12
    oft
    0.11
     chances
    0.11
    Activations Density 0.039%

    No Known Activations