© 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. 63109
    Prev
    Next
    INDEX
    Explanations

    suffixes indicating nouns or adjectives

    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
    a
    -0.11
    i
    -0.10
     tast
    -0.10
    ÂŃi
    -0.10
     LM
    -0.09
     prot
    -0.09
    714
    -0.09
    gu
    -0.09
     Scot
    -0.09
    en
    -0.09
    POSITIVE LOGITS
    надлеж
    0.11
    ismo
    0.10
     addCriterion
    0.10
    êµ
    0.10
    activex
    0.10
    antes
    0.10
     -*-č\n
    0.10
    edback
    0.09
    ozo
    0.09
    наÑģлÑĸд
    0.09
    Activations Density 0.189%

    No Known Activations