© 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. 30729
    Prev
    Next
    INDEX
    Explanations

    and followed by names or roles

    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
     explic
    -0.09
    Â
    -0.09
    vid
    -0.08
     à¤Ĺत
    -0.08
     Huff
    -0.08
     Parad
    -0.08
    ourcem
    -0.08
     innoc
    -0.08
     parad
    -0.08
    uler
    -0.08
    POSITIVE LOGITS
    æĹģ
    0.13
     myself
    0.12
    Narr
    0.12
     Narr
    0.12
     yourself
    0.10
     system
    0.10
     bystand
    0.10
     another
    0.10
    HOST
    0.10
     interchange
    0.10
    Activations Density 0.339%

    No Known Activations