© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 34954
    Prev
    Next
    INDEX
    Explanations

    simplicity, readability, versatility, stability

    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
     responsiveness
    -0.12
     attractiveness
    -0.12
     freshness
    -0.11
     cohesion
    -0.10
     openness
    -0.10
    lexible
    -0.09
     fidelity
    -0.09
     Rhe
    -0.09
     sincerity
    -0.09
     completeness
    -0.09
    POSITIVE LOGITS
     repe
    0.14
     speed
    0.13
     rig
    0.12
     utility
    0.12
     frag
    0.12
     adapt
    0.11
     univers
    0.11
     eas
    0.11
     Britt
    0.11
     expans
    0.11
    Activations Density 0.099%

    No Known Activations