© 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. 30725
    Prev
    Next
    INDEX
    Explanations

    variable assignments and code structures

    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
    bic
    -0.10
    £i
    -0.09
    635
    -0.09
    emez
    -0.09
    cente
    -0.08
    slaught
    -0.08
     Aviv
    -0.08
    itus
    -0.08
    (åľŁ
    -0.08
    /modal
    -0.08
    POSITIVE LOGITS
     plural
    0.17
    plural
    0.14
    edBy
    0.11
     themselves
    0.10
     cellForRowAt
    0.09
    ScrollIndicator
    0.09
    ạn
    0.09
     mans
    0.09
    ize
    0.09
    uais
    0.09
    Activations Density 0.356%

    No Known Activations