© 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. 2868
    Prev
    Next
    INDEX
    Explanations

    unique and descriptors

    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
    ensively
    -0.09
    007
    -0.09
    <|begin_of_text|>
    -0.08
    achi
    -0.08
    247
    -0.08
    IGN
    -0.08
     ÑĢозк
    -0.08
     Vel
    -0.08
     lesbische
    -0.08
     licensors
    -0.08
    POSITIVE LOGITS
     unique
    0.14
     original
    0.13
    /or
    0.12
    unique
    0.11
    /OR
    0.11
     Unique
    0.10
     UNIQUE
    0.10
     uniq
    0.10
     potentially
    0.10
    _UNIQUE
    0.10
    Activations Density 0.051%

    No Known Activations