© 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. 9646
    Prev
    Next
    INDEX
    Explanations

    restrict, restricted, restrictions

    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
    obe
    -0.10
    oss
    -0.10
    ãģ¨ãģĵãĤį
    -0.09
     tapped
    -0.09
     Petit
    -0.09
    rift
    -0.09
    ous
    -0.09
    ufs
    -0.08
    greg
    -0.08
    à¥įयत
    -0.08
    POSITIVE LOGITS
    ively
    0.18
    ive
    0.16
    ions
    0.16
    iveness
    0.15
     placed
    0.13
     access
    0.12
    edly
    0.12
    ainer
    0.11
    ictions
    0.11
    iven
    0.10
    Activations Density 0.036%

    No Known Activations