© 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. 35040
    Prev
    Next
    INDEX
    Explanations

    until / up to

    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
    ãģŁãģı
    -0.10
    æľŁéĸĵ
    -0.09
     eldre
    -0.08
    esteem
    -0.08
    anken
    -0.08
    giene
    -0.08
     POSSIBILITY
    -0.08
    lider
    -0.08
    jni
    -0.08
    estr
    -0.08
    POSITIVE LOGITS
     date
    0.14
    'Ãł
    0.13
    ’;Ãł
    0.12
     recently
    0.12
     dato
    0.11
     now
    0.11
     táºŃn
    0.10
    /un
    0.10
     detriment
    0.10
    -date
    0.10
    Activations Density 0.050%

    No Known Activations