© 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. 23989
    Prev
    Next
    INDEX
    Explanations

    see, find, meet, buy

    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
    åİ»äºĨ
    -0.12
    orb
    -0.10
    pedia
    -0.10
     acomp
    -0.10
    762
    -0.09
     Morr
    -0.09
     discre
    -0.09
    ner
    -0.08
    era
    -0.08
    erot
    -0.08
    POSITIVE LOGITS
    åĪ°
    0.19
     åĪ°
    0.12
    è¯Ĩ
    0.12
    èŃĺ
    0.10
    åĪ°çļĦ
    0.10
     gặp
    0.09
    åĪ°äºĨ
    0.09
    ูà¹Ī
    0.09
    NAL
    0.09
    认è¯Ĩ
    0.09
    Activations Density 0.004%

    No Known Activations