© 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. 27839
    Prev
    Next
    INDEX
    Explanations

    noticed

    np_max-act · gemini-2.0-flash

    This neuron detects the use of the verb “notice(d)” in first-person observation phrases (e.g. “I noticed that…,” “I’ve noticed in…”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    details about business processes and practices, particularly in the context of advertising and its historical evolution.

    oai_token-act-pair · gpt-4o-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
    ٥
    -0.07
    ليف
    -0.07
     screaming
    -0.07
     *=
    -0.06
     malt
    -0.06
    .Ag
    -0.06
    enco
    -0.06
    565
    -0.06
     culinary
    -0.06
    medi
    -0.06
    POSITIVE LOGITS
     noticed
    0.14
     notice
    0.13
     noticing
    0.10
     noted
    0.10
     detected
    0.08
     unnoticed
    0.08
    注意
    0.08
    _fixed
    0.08
    :::
    0.08
    aneously
    0.07
    Activations Density 0.026%

    No Known Activations