© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 16205
    Prev
    Next
    INDEX
    Explanations

    process or ability

    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
    akis
    -0.09
    rai
    -0.09
     Brun
    -0.08
    olis
    -0.08
    emony
    -0.08
     PY
    -0.08
    ÃĹ\n\n
    -0.08
     Mitt
    -0.08
     py
    -0.08
    umer
    -0.08
    POSITIVE LOGITS
     act
    0.27
     process
    0.23
     ability
    0.20
    act
    0.19
    process
    0.17
     practice
    0.17
     branch
    0.14
     proceso
    0.14
     idea
    0.14
    Process
    0.14
    Activations Density 0.097%

    No Known Activations