© 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. 42260
    Prev
    Next
    INDEX
    Explanations

    rules and statements

    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
     pla
    -0.09
    æĮĩæķ°
    -0.09
     Davidson
    -0.09
    namen
    -0.09
    cker
    -0.09
     correctness
    -0.08
     Gemini
    -0.08
     ÑĢеÑģ
    -0.08
     Bowman
    -0.08
     clustered
    -0.08
    POSITIVE LOGITS
     rule
    0.40
     rules
    0.34
     Rule
    0.33
    rule
    0.30
     Rules
    0.29
    Rule
    0.28
    -rule
    0.27
    Rules
    0.24
     RULE
    0.24
    è§Ħ
    0.24
    Activations Density 0.114%

    No Known Activations