© 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. 35425
    Prev
    Next
    INDEX
    Explanations

    guidance and direction

    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
    287
    -0.09
     troub
    -0.09
     enjo
    -0.09
     gri
    -0.09
    zie
    -0.09
     Headquarters
    -0.09
     Basis
    -0.08
     HQ
    -0.08
     ayud
    -0.08
    ãĢĢ
    -0.08
    POSITIVE LOGITS
     guidance
    0.41
     leadership
    0.37
     direction
    0.37
    direction
    0.26
     Leadership
    0.26
     Guidance
    0.25
     supervision
    0.23
     oversight
    0.23
     influence
    0.23
     Direction
    0.23
    Activations Density 0.079%

    No Known Activations