© 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. 8977
    Prev
    Next
    INDEX
    Explanations

    states that, toxic, implies

    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
    ãĥ¼ãĥķ
    -0.09
    ÑĢаÑħ
    -0.09
     Buckley
    -0.08
     Wass
    -0.08
    าà¸Ļà¸Ħร
    -0.08
     пÑĢедпол
    -0.08
    ยà¸ĩ
    -0.08
    ë¡ľëĤĺ
    -0.08
    _fu
    -0.08
     Millet
    -0.08
    POSITIVE LOGITS
     plural
    0.12
     unspecified
    0.11
    plural
    0.10
     generic
    0.10
     whereas
    0.09
    elta
    0.09
    oir
    0.09
     бÑĥдÑĤо
    0.08
     "
    0.08
    nels
    0.08
    Activations Density 0.021%

    No Known Activations