© 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. 62644
    Prev
    Next
    INDEX
    Explanations

    explaining phrases after punctuation

    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
     Tamb
    -0.09
    decltype
    -0.08
    renom
    -0.08
     mere
    -0.08
    ãģĤãģ®
    -0.08
     Bog
    -0.08
    rai
    -0.08
    873
    -0.08
    627
    -0.08
    pras
    -0.08
    POSITIVE LOGITS
     Brief
    0.16
     à¤ĩसम
    0.16
     instead
    0.15
     this
    0.14
     basically
    0.14
    ãģĵãģ¡ãĤī
    0.14
     Instead
    0.14
    Instead
    0.14
    Brief
    0.13
    è¿Ļç§į
    0.13
    Activations Density 0.152%

    No Known Activations