© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 35321
    Prev
    Next
    INDEX
    Explanations

    statement of being or action

    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
    esh
    -0.09
    aday
    -0.09
    anness
    -0.09
    æĸĹ
    -0.08
     Pang
    -0.08
    itia
    -0.08
     awhile
    -0.08
     ladder
    -0.08
    ismatch
    -0.08
    isoner
    -0.08
    POSITIVE LOGITS
    ìļĶ
    0.10
    ogo
    0.09
    ves
    0.09
    VES
    0.08
    iban
    0.08
    IPC
    0.08
    oplast
    0.08
    egen
    0.08
     unless
    0.08
    bay
    0.08
    Activations Density 0.097%

    No Known Activations