© 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. 23360
    Prev
    Next
    INDEX
    Explanations

    prompts for short written content

    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
    bjerg
    -0.11
    <|begin_of_text|>
    -0.11
    EMPLARY
    -0.11
    ******č\n
    -0.10
    ippo
    -0.10
    pekt
    -0.10
     -*-č\n
    -0.10
    ÂĢÂĢ
    -0.09
    ammable
    -0.09
    DCALL
    -0.09
    POSITIVE LOGITS
    ening
    0.17
    listed
    0.17
    -lived
    0.17
    bread
    0.16
    -form
    0.16
    -short
    0.16
    list
    0.16
    -term
    0.15
     gá»įn
    0.14
    cake
    0.14
    Activations Density 0.053%

    No Known Activations