© 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. 12556
    Prev
    Next
    INDEX
    Explanations

    code constants or literals

    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
     componentWill
    -0.11
     Stall
    -0.09
     ãĤĿ
    -0.09
    oux
    -0.09
    isor
    -0.09
     italic
    -0.09
    abb
    -0.09
    ((&
    -0.08
     Lean
    -0.08
    sov
    -0.08
    POSITIVE LOGITS
     constant
    0.27
     Constant
    0.25
    constant
    0.22
     literal
    0.21
    Constant
    0.21
     CONSTANT
    0.19
     constants
    0.19
    .constant
    0.19
    constants
    0.18
    literal
    0.16
    Activations Density 0.165%

    No Known Activations