© 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. 54866
    Prev
    Next
    INDEX
    Explanations

    greater emphasis

    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
    .gg
    -0.11
    UDGE
    -0.09
    inges
    -0.09
    ä¸ĺ
    -0.09
    (@(
    -0.09
    stanov
    -0.09
    Ħĸ
    -0.09
    pard
    -0.09
     addCriterion
    -0.09
    ToShow
    -0.08
    POSITIVE LOGITS
     emphasis
    0.27
     importance
    0.24
    emphasis
    0.23
     stress
    0.21
     premium
    0.21
    phasis
    0.20
     accent
    0.20
     Importance
    0.20
     value
    0.19
     priority
    0.19
    Activations Density 0.008%

    No Known Activations