© 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. 42115
    Prev
    Next
    INDEX
    Explanations

    types of

    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
    [section
    -0.09
     localVar
    -0.08
    ocab
    -0.08
    é¾Ħ
    -0.08
     yyn
    -0.08
    fak
    -0.08
    362
    -0.08
    ril
    -0.08
     fkk
    -0.08
    xmm
    -0.08
    POSITIVE LOGITS
     responses
    0.09
     methods
    0.09
     damages
    0.09
     resets
    0.09
     sources
    0.09
     errors
    0.09
    æħĭ
    0.09
     ways
    0.09
    teri
    0.09
     bang
    0.08
    Activations Density 0.119%

    No Known Activations