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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 887
    Prev
    Next
    INDEX
    Explanations

    advancing AI technology

    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
    emet
    -0.09
     mots
    -0.09
    inic
    -0.09
     поба
    -0.09
    ifar
    -0.09
     Saunders
    -0.08
    alah
    -0.08
    æ¸Ī
    -0.08
    rica
    -0.08
    erval
    -0.08
    POSITIVE LOGITS
     continue
    0.21
     continues
    0.21
    continue
    0.16
     ne
    0.16
     becomes
    0.15
    \tcontinue
    0.15
    继ç»Ń
    0.14
     пÑĢодолж
    0.13
     become
    0.12
     continued
    0.12
    Activations Density 0.050%

    No Known Activations