© 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. 41714
    Prev
    Next
    INDEX
    Explanations

    grouping with other items

    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
     acronym
    -0.10
     Bilg
    -0.10
     Floral
    -0.09
     ragaz
    -0.09
    PURE
    -0.09
    Verb
    -0.09
    )did
    -0.09
     shorthand
    -0.09
     abbrev
    -0.09
    ｿ
    -0.09
    POSITIVE LOGITS
     word
    0.11
     item
    0.11
     singular
    0.10
     Cup
    0.10
     Word
    0.10
     object
    0.10
    Word
    0.10
     ðŁ
    0.10
     itemType
    0.09
    item
    0.09
    Activations Density 0.214%

    No Known Activations