© 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. 24700
    Prev
    Next
    INDEX
    Explanations

    significant events after "the"

    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
     Completion
    -0.09
    _handling
    -0.09
    new
    -0.09
     hostage
    -0.09
     handling
    -0.08
     meny
    -0.08
     advancing
    -0.08
     cand
    -0.08
     new
    -0.08
     refusing
    -0.08
    POSITIVE LOGITS
     creation
    0.16
     formation
    0.15
     deaths
    0.15
     possibility
    0.12
     development
    0.12
     appearance
    0.12
     displacement
    0.12
     birth
    0.12
     formations
    0.12
     establishment
    0.11
    Activations Density 0.046%

    No Known Activations