© 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. 51607
    Prev
    Next
    INDEX
    Explanations

    be followed by action verbs

    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
     použÃŃ
    -0.10
    èĥ½å¤Ł
    -0.09
    asca
    -0.09
    ething
    -0.09
     verwenden
    -0.09
    aal
    -0.09
    ä¸Ģå®ļ
    -0.09
     kullanı
    -0.09
     ıs
    -0.09
    arım
    -0.09
    POSITIVE LOGITS
     easily
    0.17
    friend
    0.14
    get
    0.12
     accessed
    0.11
    amed
    0.11
     best
    0.11
     Easily
    0.11
     done
    0.11
    fall
    0.11
     seen
    0.11
    Activations Density 0.049%

    No Known Activations