© 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. 8722
    Prev
    Next
    INDEX
    Explanations

    cannot answer or discuss

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

    expressions of inability or unwillingness to do something.

    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
    iske
    -0.09
     Tus
    -0.08
     Presenter
    -0.08
    larg
    -0.08
    igid
    -0.08
    igit
    -0.08
    éĸĵ
    -0.08
     reusable
    -0.08
    ëħ
    -0.08
     mappedBy
    -0.08
    POSITIVE LOGITS
     answer
    0.24
     comment
    0.23
     discuss
    0.21
     discussion
    0.18
    answer
    0.17
     discussing
    0.17
     Answer
    0.17
    åĽŀçŃĶ
    0.17
     answered
    0.16
     Comment
    0.16
    Activations Density 0.125%

    No Known Activations