© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 33936
    Prev
    Next
    INDEX
    Explanations

    all the, all relationships, all interactions, all your

    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
    untas
    -0.09
    /loose
    -0.09
     possibilities
    -0.09
    etable
    -0.08
    spb
    -0.08
    796
    -0.08
     rval
    -0.08
    åĵģ
    -0.08
    510
    -0.08
     Thom
    -0.08
    POSITIVE LOGITS
     aspect
    0.26
     aspects
    0.25
    æĸ¹éĿ¢
    0.20
    aspect
    0.20
    Aspect
    0.19
     Aspect
    0.17
     interactions
    0.15
    pects
    0.14
     аÑģп
    0.14
     dealings
    0.13
    Activations Density 0.029%

    No Known Activations