© 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. 24757
    Prev
    Next
    INDEX
    Explanations

    common themes, often explored

    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
     contrad
    -0.12
     contradictions
    -0.11
    ''"
    -0.10
     fug
    -0.10
     contradict
    -0.10
     rational
    -0.10
    irit
    -0.09
     丶
    -0.09
     lee
    -0.09
     notions
    -0.09
    POSITIVE LOGITS
     Straw
    0.19
     straw
    0.18
    Compat
    0.13
     slogan
    0.13
     elimin
    0.12
     Raw
    0.12
     Scot
    0.12
     slippery
    0.12
    Raw
    0.11
     circular
    0.11
    Activations Density 0.094%

    No Known Activations