© 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. 15192
    Prev
    Next
    INDEX
    Explanations

    purpose, opposite, subvert

    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
     ::::::::
    -0.11
    ä¸į足
    -0.09
     improperly
    -0.09
    @student
    -0.08
    isNew
    -0.08
     Hast
    -0.08
    )did
    -0.08
     defer
    -0.08
    ména
    -0.08
    >[]
    -0.08
    POSITIVE LOGITS
    æķħ
    0.22
     purpose
    0.21
     opposite
    0.20
    Purpose
    0.19
    purpose
    0.18
     Purpose
    0.18
     deliber
    0.16
     PURPOSE
    0.15
    -purpose
    0.15
     reverse
    0.15
    Activations Density 0.336%

    No Known Activations