© 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. 14753
    Prev
    Next
    INDEX
    Explanations

    point cloud handle

    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
     ven
    -0.11
     Ven
    -0.10
     Dar
    -0.09
     venom
    -0.09
     Nash
    -0.09
    _firstname
    -0.09
    -pad
    -0.09
     unr
    -0.09
     diff
    -0.08
     mains
    -0.08
    POSITIVE LOGITS
     birth
    0.11
     Arnold
    0.11
     prim
    0.10
     AttributeSet
    0.10
    GRP
    0.10
     Maya
    0.10
    _ATTRIB
    0.09
     Attribute
    0.09
    èIJ¥ä¸ļ
    0.09
    Attrib
    0.09
    Activations Density 0.023%

    No Known Activations