© 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. 26374
    Prev
    Next
    INDEX
    Explanations

    defining scope and problem

    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
     specified
    -0.10
     Jal
    -0.09
    İ·
    -0.09
     specificity
    -0.08
     solutions
    -0.08
    wdx
    -0.08
     Whip
    -0.08
     provision
    -0.08
     Suggestions
    -0.08
    .scalablytyped
    -0.08
    POSITIVE LOGITS
     scope
    0.23
     Scope
    0.18
    scope
    0.17
    Scope
    0.15
    SCO
    0.15
     boundaries
    0.14
     following
    0.14
     problem
    0.14
     Problem
    0.14
    (scope
    0.14
    Activations Density 0.112%

    No Known Activations