© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 14307
    Prev
    Next
    INDEX
    Explanations

    wars of religion

    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
     salopes
    -0.12
    βολ
    -0.10
    798
    -0.10
     Laurent
    -0.09
     Liber
    -0.09
    pees
    -0.09
    strand
    -0.09
    APER
    -0.09
    ateg
    -0.09
    Bonjour
    -0.09
    POSITIVE LOGITS
    157
    0.23
    156
    0.23
    158
    0.18
    159
    0.16
    155
    0.15
     Calvin
    0.13
    154
    0.13
     Protest
    0.13
     hug
    0.12
    161
    0.12
    Activations Density 0.031%

    No Known Activations