© 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. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 110663
    Prev
    Next
    INDEX
    Explanations

    focus

    np_max-act · gemini-2.0-flash

    The neuron activates on the token “focus,” i.e. it detects occurrences of the word “focus” (as in “focus groups” or “focus sessions”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Amsterdam
    -0.07
     alternating
    -0.07
     Marl
    -0.07
     Anne
    -0.07
    羊
    -0.07
     recht
    -0.06
    _TRAN
    -0.06
     reint
    -0.06
    rent
    -0.06
    chem
    -0.06
    POSITIVE LOGITS
     focus
    0.15
     Focus
    0.14
    focus
    0.13
    Focus
    0.12
     focusing
    0.12
     focused
    0.12
    focused
    0.11
     foc
    0.09
     focuses
    0.09
     autofocus
    0.09
    Activations Density 0.028%

    No Known Activations