© 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. 57846
    Prev
    Next
    INDEX
    Explanations

    against, against, against

    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
    atcher
    -0.08
    breadcrumbs
    -0.08
     controvers
    -0.08
    avo
    -0.08
     lit
    -0.08
    izik
    -0.08
    ighter
    -0.08
    ï¼
    -0.08
    ثار
    -0.08
    éĢļãĤĬ
    -0.08
    POSITIVE LOGITS
     against
    0.94
     Against
    0.75
    against
    0.74
    Against
    0.67
     contre
    0.56
     gegen
    0.54
     пÑĢоÑĤи
    0.54
     proti
    0.53
     tegen
    0.50
     ضد
    0.47
    Activations Density 0.115%

    No Known Activations