© 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. 33461
    Prev
    Next
    INDEX
    Explanations

    giving examples

    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
    ayne
    -0.12
    ronym
    -0.10
    .CG
    -0.09
    lacak
    -0.09
    üven
    -0.09
    oeff
    -0.09
    atest
    -0.09
    ÃĮ
    -0.08
    EDI
    -0.08
    utsch
    -0.08
    POSITIVE LOGITS
     purposes
    0.21
     sake
    0.20
     if
    0.16
    ãģĪãģ°
    0.14
    :
    0.10
     If
    0.10
     given
    0.10
     jika
    0.10
     earlier
    0.10
    å¦Ĥæŀľ
    0.10
    Activations Density 0.016%

    No Known Activations