© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 32805
    Prev
    Next
    INDEX
    Explanations

    agents to take actions

    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
    pig
    -0.10
    857
    -0.10
     Lincoln
    -0.09
    rance
    -0.09
     nick
    -0.09
    trer
    -0.09
    opsis
    -0.09
    rones
    -0.09
    HEMA
    -0.09
     ze
    -0.09
    POSITIVE LOGITS
     actions
    0.18
     agents
    0.16
     agent
    0.15
     policy
    0.15
     policies
    0.14
     Agents
    0.14
     action
    0.14
     decision
    0.14
    actions
    0.13
     Policy
    0.13
    Activations Density 0.039%

    No Known Activations