© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 37692
    Prev
    Next
    INDEX
    Explanations

    you followed by a verb

    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
    ceipt
    -0.09
     Heath
    -0.09
     migrationBuilder
    -0.09
    lobal
    -0.08
    kest
    -0.08
    oldemort
    -0.08
    SetBranch
    -0.08
    VERR
    -0.08
     clue
    -0.08
    igon
    -0.08
    POSITIVE LOGITS
     previous
    0.16
     earlier
    0.13
     previously
    0.12
     seem
    0.11
     seemed
    0.11
    previous
    0.11
     initially
    0.10
     originally
    0.10
     seems
    0.10
     response
    0.10
    Activations Density 0.020%

    No Known Activations