© 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. 40100
    Prev
    Next
    INDEX
    Explanations

    synapse, synthesize, synonyms

    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
    ¿
    -0.09
    asted
    -0.09
    ën
    -0.09
    XP
    -0.09
    antaged
    -0.09
    toa
    -0.09
     refr
    -0.08
    аÑĢÑĩ
    -0.08
    unting
    -0.08
    undi
    -0.08
    POSITIVE LOGITS
    opsis
    0.18
    thesis
    0.17
    OPSIS
    0.15
    cret
    0.14
    ners
    0.13
    apse
    0.13
     Syn
    0.13
    ringe
    0.12
    ucle
    0.12
    s
    0.12
    Activations Density 0.023%

    No Known Activations