© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 27699
    Prev
    Next
    INDEX
    Explanations

    parsing text and data

    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
    ted
    -0.12
    nement
    -0.11
    _parser
    -0.10
    ally
    -0.10
     phẩm
    -0.09
    ìĶ©
    -0.09
    iveness
    -0.09
    anness
    -0.09
     Lem
    -0.09
    ancy
    -0.09
    POSITIVE LOGITS
    .parse
    0.15
    _qs
    0.13
    .Parse
    0.13
    (Parse
    0.11
    (Parser
    0.10
    ible
    0.10
    .Parser
    0.10
    imony
    0.10
    .ParseException
    0.09
    inton
    0.09
    Activations Density 0.024%

    No Known Activations