© 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. 34239
    Prev
    Next
    INDEX
    Explanations

    polite requests followed by punctuation

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

    polite request words like "please" (and its equivalents in other languages).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @yooniel31
    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
    įng
    -0.12
    EMPLARY
    -0.11
    ¶Į
    -0.10
    ¦æĥħ
    -0.10
    .IsNullOr
    -0.10
    ******č\n
    -0.10
     Leban
    -0.09
    PageRoute
    -0.09
    åĺĽ
    -0.09
    łéĻ¤
    -0.09
    POSITIVE LOGITS
    ï¿
    0.09
     Tol
    0.08
    ](
    0.08
    è°¢
    0.08
    ?\n\n
    0.08
    ight
    0.08
    XXXX
    0.08
    ?\n
    0.08
    ⣩
    0.08
     otherwise
    0.08
    Activations Density 0.291%

    No Known Activations