© 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. 36520
    Prev
    Next
    INDEX
    Explanations

    struck, striking, strikes followed by context

    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
    ãģĬãĤĬ
    -0.11
    nt
    -0.11
    ynes
    -0.11
    estic
    -0.10
    lien
    -0.09
    rou
    -0.09
     ãĢĢ
    -0.09
    754
    -0.09
     satisf
    -0.09
    ãģĦãģ¾ãģĻ
    -0.09
    POSITIVE LOGITS
    out
    0.15
     struck
    0.14
     fear
    0.13
    strike
    0.13
     strike
    0.12
     blow
    0.12
     Strike
    0.12
     chord
    0.12
     blows
    0.12
     terror
    0.11
    Activations Density 0.014%

    No Known Activations