© 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. 42058
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives

    np_acts-logits-general · gemini-2.5-flash-lite

    descriptive adjectives and other content-heavy modifiers indicating qualities or characteristics, across multiple languages.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    ¶Į
    -0.18
    ******č\n
    -0.14
    įng
    -0.14
     -*-č\n
    -0.14
    ÂĢÂĢ
    -0.12
    ¡ng
    -0.12
    .Dictionary
    -0.12
    .Formatter
    -0.11
    ³ç´°
    -0.11
    ¨ë¶Ģ
    -0.11
    POSITIVE LOGITS
    /in
    0.07
    .scalablytyped
    0.07
     "'
    0.07
    -se
    0.06
    /n
    0.06
     prob
    0.06
     BEFORE
    0.06
    /se
    0.06
    /ch
    0.06
    ize
    0.06
    Activations Density 5.115%

    No Known Activations