© 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. 52027
    Prev
    Next
    INDEX
    Explanations

    regex anchors

    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
    969
    -0.09
     trai
    -0.09
     Hunger
    -0.09
    ANGUAGE
    -0.09
     misc
    -0.09
     Deep
    -0.08
     Colon
    -0.08
    744
    -0.08
     Gros
    -0.08
    .AutoComplete
    -0.08
    POSITIVE LOGITS
     anchors
    0.16
    anch
    0.13
    anchors
    0.13
     Anchor
    0.13
    ANCH
    0.12
     boundaries
    0.12
     quant
    0.12
     anchor
    0.12
     Flags
    0.12
     flags
    0.12
    Activations Density 0.021%

    No Known Activations