© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 38099
    Prev
    Next
    INDEX
    Explanations

    give specific examples or details

    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
     McCart
    -0.09
     Nack
    -0.09
    plib
    -0.09
    .dk
    -0.09
    uzzi
    -0.08
    ogr
    -0.08
    407
    -0.08
     Dro
    -0.08
    lland
    -0.08
     sın
    -0.08
    POSITIVE LOGITS
     examples
    0.19
    äºĪ
    0.14
    examples
    0.14
     pros
    0.12
     Examples
    0.12
    away
    0.12
    å®ĥ们
    0.12
     example
    0.12
    _examples
    0.12
    ä¾ĭ
    0.11
    Activations Density 0.037%

    No Known Activations