© 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. 21745
    Prev
    Next
    INDEX
    Explanations

    explaining why something is

    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
    andle
    -0.10
     certainly
    -0.09
     Hyde
    -0.09
    Disposed
    -0.09
    uer
    -0.09
    Hints
    -0.09
    autos
    -0.09
     TOO
    -0.09
    /epl
    -0.09
     mel
    -0.08
    POSITIVE LOGITS
    å¦ĤæѤ
    0.17
     so
    0.17
     à¤ĩतन
    0.16
     tolik
    0.15
    è¿Ļä¹Ī
    0.14
    éĤ£ä¹Ī
    0.13
     suddenly
    0.12
     Important
    0.12
     così
    0.12
    why
    0.11
    Activations Density 0.125%

    No Known Activations