© 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. 23972
    Prev
    Next
    INDEX
    Explanations

    if clauses and possibilities

    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
     Bonus
    -0.10
    ycler
    -0.09
    _subset
    -0.09
     Alo
    -0.09
    ymes
    -0.09
    lando
    -0.09
    edo
    -0.09
    ower
    -0.08
     ÑģÑĤаÑĢа
    -0.08
     garn
    -0.08
    POSITIVE LOGITS
     mind
    0.20
     Mind
    0.17
    mind
    0.15
    Mind
    0.15
     minds
    0.14
     ever
    0.14
     could
    0.14
     willing
    0.13
     minded
    0.13
     willingness
    0.13
    Activations Density 0.061%

    No Known Activations