© 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. 55701
    Prev
    Next
    INDEX
    Explanations

    my purpose

    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
     centr
    -0.09
    _subplot
    -0.09
     locations
    -0.09
    êµ
    -0.09
    пÑĢиклад
    -0.09
     NAT
    -0.08
     gross
    -0.08
    olta
    -0.08
     "
    -0.08
    oir
    -0.08
    POSITIVE LOGITS
     purpose
    0.26
     goal
    0.25
     aim
    0.21
    purpose
    0.18
     objective
    0.18
     priority
    0.18
     primary
    0.17
     job
    0.17
    goal
    0.15
     intention
    0.15
    Activations Density 0.028%

    No Known Activations