© 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. 9719
    Prev
    Next
    INDEX
    Explanations

    credibility and expertise

    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
    atty
    -0.10
     Mits
    -0.09
     chew
    -0.09
     actionable
    -0.09
     âĮĴ
    -0.09
     Spinner
    -0.08
     cliff
    -0.08
    ples
    -0.08
    alu
    -0.08
     absol
    -0.08
    POSITIVE LOGITS
     authority
    0.38
     credibility
    0.34
     Authority
    0.30
    Authority
    0.28
    authority
    0.28
    cred
    0.23
     trust
    0.22
     cred
    0.22
    _cred
    0.22
    credible
    0.21
    Activations Density 0.076%

    No Known Activations