© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 44342
    Prev
    Next
    INDEX
    Explanations

    removing components from contexts

    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
     cred
    -0.09
    chant
    -0.09
    orris
    -0.09
    vat
    -0.08
    á»Ļc
    -0.08
    Facade
    -0.08
     пÑĢоиÑģ
    -0.08
    238
    -0.08
     peeled
    -0.08
    733
    -0.08
    POSITIVE LOGITS
     khá»ıi
    0.47
     from
    0.32
     från
    0.23
    from
    0.22
     từ
    0.19
     αÏĢÏĮ
    0.18
     از
    0.18
    à¸Īาà¸ģ
    0.18
     dari
    0.17
     off
    0.17
    Activations Density 0.114%

    No Known Activations