© 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. 56660
    Prev
    Next
    INDEX
    Explanations

    dog actions and states

    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
    æij¸
    -0.11
    ToWorld
    -0.10
     unarmed
    -0.10
    ä¸Ī
    -0.10
    cles
    -0.10
     ensl
    -0.09
     Gather
    -0.09
    .Framework
    -0.09
     Craw
    -0.09
    odate
    -0.09
    POSITIVE LOGITS
     vocal
    0.13
     bark
    0.13
     destructive
    0.11
     mia
    0.11
     sul
    0.11
    èĪ
    0.11
     terror
    0.11
    mae
    0.10
     gamb
    0.10
     ur
    0.10
    Activations Density 0.104%

    No Known Activations