© 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. 34316
    Prev
    Next
    INDEX
    Explanations

    sources tell or have

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

    attributions in news articles that cite sources or officials.

    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
     rumours
    -0.09
     recount
    -0.09
     announcing
    -0.09
    ieber
    -0.09
     announc
    -0.09
     coverage
    -0.09
     announcement
    -0.08
     Bauer
    -0.08
    éĺ
    -0.08
     recorded
    -0.08
    POSITIVE LOGITS
     sources
    0.30
    sources
    0.23
     Sources
    0.22
    Sources
    0.21
     source
    0.19
     иÑģÑĤоÑĩ
    0.19
     nguá»ĵn
    0.17
    ources
    0.16
     reliable
    0.16
    _sources
    0.15
    Activations Density 0.082%

    No Known Activations