© 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. 56769
    Prev
    Next
    INDEX
    Explanations

    chasing fictional prey

    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
     Fighting
    -0.11
     fighting
    -0.11
     Fight
    -0.09
     boca
    -0.09
    leftright
    -0.09
     Trojan
    -0.09
    882
    -0.09
     struggling
    -0.08
     hostage
    -0.08
     Explorer
    -0.08
    POSITIVE LOGITS
    追
    0.55
     pursuit
    0.42
     chase
    0.38
     pursue
    0.37
     purs
    0.37
     Purs
    0.37
     pursued
    0.35
     pursuing
    0.33
     пÑĢеÑģ
    0.30
    CHASE
    0.30
    Activations Density 0.072%

    No Known Activations