© 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. 29699
    Prev
    Next
    INDEX
    Explanations

    names after conjunctions or greetings

    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
    andest
    -0.09
    amas
    -0.09
    REA
    -0.08
    iffies
    -0.08
    maxlength
    -0.08
    á»ĭch
    -0.08
     Miche
    -0.08
     Amerik
    -0.08
     Buckley
    -0.08
    дейÑģÑĤв
    -0.08
    POSITIVE LOGITS
     Mentor
    0.09
    asso
    0.08
     cong
    0.08
     Burns
    0.07
     @_
    0.07
    Ë
    0.07
     bei
    0.07
     èī
    0.07
    con
    0.07
    BF
    0.07
    Activations Density 0.119%

    No Known Activations