© 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. 24134
    Prev
    Next
    INDEX
    Explanations

    examining, examination, examens

    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
    teness
    -0.11
    fully
    -0.11
    ष
    -0.10
    fulness
    -0.10
    ted
    -0.10
    ward
    -0.10
    /editor
    -0.09
    oric
    -0.09
    ayet
    -0.09
    637
    -0.09
    POSITIVE LOGITS
    iners
    0.20
    ined
    0.15
    INED
    0.15
    INATION
    0.14
    ining
    0.14
     closely
    0.13
    inant
    0.13
    inar
    0.12
    inate
    0.12
    GenerationStrategy
    0.11
    Activations Density 0.020%

    No Known Activations