© 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. 51227
    Prev
    Next
    INDEX
    Explanations

    verb and another verb

    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
    ɵ
    -0.11
    iasi
    -0.08
    ;
    -0.08
    laden
    -0.08
     eller
    -0.08
     veya
    -0.08
    otify
    -0.07
    ugo
    -0.07
    :
    -0.07
     SKU
    -0.07
    POSITIVE LOGITS
     and
    0.28
     vÃł
    0.25
     и
    0.23
    à¹ģละ
    0.21
    并
    0.21
     à¤Ķर
    0.20
     ÈĻi
    0.20
     és
    0.19
     και
    0.19
    並
    0.17
    Activations Density 0.388%

    No Known Activations