© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 11684
    Prev
    Next
    INDEX
    Explanations

    working together

    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
    sWith
    -0.12
     work
    -0.09
    uhan
    -0.09
     collectively
    -0.09
    eller
    -0.09
     actionTypes
    -0.09
    ABCDEFGHIJKLMNOP
    -0.09
     Gilbert
    -0.09
     Barrel
    -0.09
     neglig
    -0.09
    POSITIVE LOGITS
     closely
    0.18
     toward
    0.16
     Äijá»ĥ
    0.16
     towards
    0.15
    erc
    0.11
     ÑĩÑĤобÑĭ
    0.10
     to
    0.10
    uzu
    0.10
     spirit
    0.10
    anne
    0.09
    Activations Density 0.016%

    No Known Activations