© 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. 51927
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by an action verb

    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
     Lod
    -0.11
     exit
    -0.10
    IPP
    -0.10
     Ambient
    -0.09
     pocket
    -0.09
    itals
    -0.09
    istle
    -0.09
     HT
    -0.09
     grown
    -0.09
    emoc
    -0.09
    POSITIVE LOGITS
     shower
    0.19
     Shower
    0.18
     collapse
    0.17
     showers
    0.15
     collapsing
    0.15
     collapsed
    0.15
    collapse
    0.14
     Collapse
    0.13
    unpack
    0.13
     collapses
    0.12
    Activations Density 0.030%

    No Known Activations