© 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. 26302
    Prev
    Next
    INDEX
    Explanations

    how to instructions

    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
    'gc
    -0.11
     learn
    -0.10
     learns
    -0.10
    561
    -0.10
    .pb
    -0.09
    _marshall
    -0.09
     try
    -0.09
    âĢ
    -0.09
    Learn
    -0.08
    +offset
    -0.08
    POSITIVE LOGITS
     properly
    0.15
     best
    0.15
     Approach
    0.13
     approach
    0.13
     proceed
    0.13
    /how
    0.12
     Proper
    0.12
    æīįèĥ½
    0.12
     spot
    0.11
    /not
    0.11
    Activations Density 0.055%

    No Known Activations