© 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. 61709
    Prev
    Next
    INDEX
    Explanations

    now experiencing

    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
    åı
    -0.09
     balk
    -0.09
     Ok
    -0.09
     Cyr
    -0.09
     OK
    -0.09
     friendly
    -0.09
    cly
    -0.09
    vt
    -0.08
     Friendly
    -0.08
    atter
    -0.08
    POSITIVE LOGITS
    éģĩ
    0.53
     encounter
    0.52
     encountered
    0.44
     encounters
    0.42
     Encounter
    0.42
     gặp
    0.39
     encount
    0.33
     encountering
    0.32
     encuent
    0.25
     rencontr
    0.25
    Activations Density 0.133%

    No Known Activations