© 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. 19623
    Prev
    Next
    INDEX
    Explanations

    ob prefix

    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
    l
    -0.10
     Chall
    -0.10
    733
    -0.09
    eum
    -0.09
    erial
    -0.09
    rition
    -0.09
    ores
    -0.09
    antee
    -0.09
    lej
    -0.09
    yb
    -0.08
    POSITIVE LOGITS
     ob
    0.18
    (ob
    0.12
    -ob
    0.11
    serve
    0.11
    isp
    0.11
     Ob
    0.11
    iously
    0.11
    EDIA
    0.10
    ser
    0.10
    itorio
    0.10
    Activations Density 0.022%

    No Known Activations