© 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. 780
    Prev
    Next
    INDEX
    Explanations

    involvement, participation, implicated

    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
    inho
    -0.11
    ale
    -0.11
    ilst
    -0.10
    inha
    -0.09
    ically
    -0.09
    ers
    -0.09
     wel
    -0.09
    InProgress
    -0.09
     duk
    -0.09
     ditch
    -0.09
    POSITIVE LOGITS
     involvement
    0.14
    vement
    0.14
    ment
    0.12
     participation
    0.12
     вов
    0.11
     ÑĥÑĩаÑģÑĤие
    0.11
    ìĭľíĤ¤
    0.11
    å«Į
    0.11
     Participation
    0.10
    nut
    0.10
    Activations Density 0.033%

    No Known Activations