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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 925
    Prev
    Next
    INDEX
    Explanations

    numbers and ranges

    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
    unden
    -0.09
    CFG
    -0.09
    defaults
    -0.09
    aln
    -0.09
    hazi
    -0.09
    ativity
    -0.09
     fast
    -0.09
    ndl
    -0.09
     ST
    -0.08
    icamente
    -0.08
    POSITIVE LOGITS
    /+
    0.13
    inci
    0.12
     Ess
    0.10
     spd
    0.09
    tes
    0.09
    жд
    0.09
     ÑģпоÑĢ
    0.09
    phet
    0.09
    odd
    0.09
    olk
    0.08
    Activations Density 0.043%

    No Known Activations