© 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. 31286
    Prev
    Next
    INDEX
    Explanations

    prove that/to/its

    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
     Briggs
    -0.10
     precision
    -0.10
     å£
    -0.10
    erk
    -0.09
     Roe
    -0.09
    waves
    -0.09
    escal
    -0.09
     prestige
    -0.09
     Dixon
    -0.09
    trl
    -0.08
    POSITIVE LOGITS
    edores
    0.17
    anced
    0.16
    ance
    0.14
     itself
    0.13
    zano
    0.13
    iences
    0.12
     himself
    0.11
    ience
    0.11
    /dis
    0.11
     doub
    0.11
    Activations Density 0.018%

    No Known Activations