© 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. 24468
    Prev
    Next
    INDEX
    Explanations

    teams or groups

    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
     Peer
    -0.09
     Dit
    -0.09
     compart
    -0.09
     Relatives
    -0.08
     Evel
    -0.08
     contingency
    -0.08
     Barnett
    -0.08
    ãģ³
    -0.08
    adian
    -0.08
     Klo
    -0.08
    POSITIVE LOGITS
     team
    0.77
     teams
    0.62
    team
    0.57
     Team
    0.51
    ãĥģãĥ¼ãĥł
    0.50
    -team
    0.48
    Team
    0.48
    teams
    0.46
    _team
    0.45
    (team
    0.45
    Activations Density 0.157%

    No Known Activations