© 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. 43026
    Prev
    Next
    INDEX
    Explanations

    sentence improvement and rewriting

    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
     Transcript
    -0.10
    ask
    -0.10
     impr
    -0.10
     complete
    -0.09
     transcription
    -0.09
     bas
    -0.09
     coarse
    -0.09
    angi
    -0.09
    çŃĶæ¡Ī
    -0.09
     Speaker
    -0.09
    POSITIVE LOGITS
     sentence
    0.20
     passive
    0.18
     Passive
    0.15
     Sentence
    0.14
    sentence
    0.14
     sentences
    0.13
     awkward
    0.12
    åı¥
    0.12
    Sentence
    0.11
    _sentence
    0.11
    Activations Density 0.175%

    No Known Activations