© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 43242
    Prev
    Next
    INDEX
    Explanations

    control related measures

    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
     controls
    -0.10
     regrets
    -0.09
     costly
    -0.09
    _controls
    -0.09
     Vid
    -0.09
    io
    -0.09
    Ĥ¹
    -0.08
     Horny
    -0.08
    -controls
    -0.08
    oodle
    -0.08
    POSITIVE LOGITS
    (Control
    0.13
     destiny
    0.12
    miner
    0.10
     Freak
    0.10
    áo
    0.10
     Cush
    0.09
     еÑģÑĤе
    0.09
     Brush
    0.09
    UBY
    0.09
    etti
    0.09
    Activations Density 0.082%

    No Known Activations