© 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. 44
    Prev
    Next
    INDEX
    Explanations

    importance to abstract concepts or speech

    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
    okes
    -0.10
    raises
    -0.09
     Appears
    -0.09
     seems
    -0.09
    GIN
    -0.09
    inel
    -0.09
     könnte
    -0.09
     ATL
    -0.09
     tall
    -0.09
     appears
    -0.08
    POSITIVE LOGITS
    æīį
    0.12
     counts
    0.12
     shouldn
    0.11
     truly
    0.11
     matters
    0.10
     IS
    0.10
     is
    0.10
    Counts
    0.10
     preced
    0.10
    areth
    0.10
    Activations Density 0.133%

    No Known Activations