© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 35702
    Prev
    Next
    INDEX
    Explanations

    step toward(s)

    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
     Throughout
    -0.10
    غات
    -0.09
    yun
    -0.09
    _crossentropy
    -0.09
     å·
    -0.08
    ú
    -0.08
    ila
    -0.08
    ENCES
    -0.08
    umer
    -0.08
    onyms
    -0.08
    POSITIVE LOGITS
     towards
    0.63
     toward
    0.62
     hacia
    0.39
     Towards
    0.39
    Towards
    0.39
     Tow
    0.36
    owards
    0.34
    oward
    0.33
    åIJij
    0.33
     verso
    0.31
    Activations Density 0.069%

    No Known Activations