© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 57186
    Prev
    Next
    INDEX
    Explanations

    an analogy

    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
     Pron
    -0.13
     acronym
    -0.12
    pron
    -0.11
     abbrev
    -0.11
     pronounce
    -0.10
     pronunciation
    -0.10
     abbreviation
    -0.10
     pronounced
    -0.10
     تÙĦÙģ
    -0.09
     Abb
    -0.09
    POSITIVE LOGITS
     metaphor
    0.40
     figur
    0.26
     metaph
    0.26
     phrase
    0.24
    phrase
    0.22
     term
    0.22
     literal
    0.22
     reference
    0.22
     analogy
    0.20
     expression
    0.19
    Activations Density 0.302%

    No Known Activations