© 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. 26223
    Prev
    Next
    INDEX
    Explanations

    control or harness abilities

    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
     )\n\n\n\n\n\n\n\n
    -0.10
     indef
    -0.09
    agenta
    -0.09
    elop
    -0.09
     subordinate
    -0.09
     entr
    -0.09
     tender
    -0.09
     Holmes
    -0.08
    fon
    -0.08
     hol
    -0.08
    POSITIVE LOGITS
     powers
    0.23
     abilities
    0.22
    powers
    0.17
     Gifts
    0.17
     Powers
    0.17
     Abilities
    0.16
    abilities
    0.16
    gift
    0.14
    Harness
    0.14
     gifts
    0.14
    Activations Density 0.071%

    No Known Activations