© 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. 40353
    Prev
    Next
    INDEX
    Explanations

    historical context and formation

    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
     ancient
    -0.11
     former
    -0.11
     Pyramid
    -0.10
     Screw
    -0.10
    olis
    -0.10
    former
    -0.10
     unlimited
    -0.09
     pyramid
    -0.09
     earliest
    -0.09
     extinct
    -0.09
    POSITIVE LOGITS
     fell
    0.11
    Ownership
    0.10
     ownership
    0.10
     became
    0.10
     Consort
    0.09
     neglect
    0.09
     devast
    0.09
    archs
    0.09
     again
    0.09
    ownership
    0.09
    Activations Density 0.043%

    No Known Activations