© 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. 26007
    Prev
    Next
    INDEX
    Explanations

    events followed by context

    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
     preceded
    -0.11
     Hicks
    -0.09
     ÙħÙħÙĨ
    -0.09
    -alist
    -0.09
     undo
    -0.09
     extrem
    -0.08
    ¶Į
    -0.08
    seite
    -0.08
     offered
    -0.08
     preval
    -0.08
    POSITIVE LOGITS
     gone
    0.13
     happened
    0.12
     conducted
    0.11
    åıijçĶŁ
    0.11
     Gone
    0.11
    gone
    0.11
     earlier
    0.10
     пÑĢоизоÑĪ
    0.10
     diá»ħn
    0.10
     that
    0.09
    Activations Density 0.151%

    No Known Activations