© 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. 60723
    Prev
    Next
    INDEX
    Explanations

    adjectives describing categories or functions

    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
    ally
    -0.17
    ality
    -0.13
    ually
    -0.12
    alth
    -0.11
    als
    -0.10
    icol
    -0.10
     addCriterion
    -0.10
    uality
    -0.09
    eza
    -0.09
    álnÃŃ
    -0.09
    POSITIVE LOGITS
    ists
    0.18
    ist
    0.16
    y
    0.12
    ism
    0.11
    -cultural
    0.11
    ISTS
    0.11
    isten
    0.11
    -functional
    0.11
    gorithm
    0.11
    -transitional
    0.11
    Activations Density 0.066%

    No Known Activations