© 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. 14189
    Prev
    Next
    INDEX
    Explanations

    æ¯Ķè¾ĥ 好

    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
    çĽijåIJ¬é¡µéĿ¢
    -0.12
    éĺħ读次æķ°
    -0.11
     /:
    -0.10
     fant
    -0.10
     Prov
    -0.10
     Humb
    -0.09
    Accessible
    -0.09
    移åĪ°
    -0.09
    820
    -0.09
     Gib
    -0.09
    POSITIVE LOGITS
    欧ç¾İ
    0.11
    unts
    0.11
     accord
    0.10
     Rational
    0.10
    ivalence
    0.09
     multiples
    0.09
    VRT
    0.09
    anter
    0.09
    oner
    0.09
    plusplus
    0.09
    Activations Density 0.098%

    No Known Activations