© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 92314
    Prev
    Next
    INDEX
    Explanations

    Questions

    np_max-act · gemini-2.0-flash

    This neuron detects question openings, i.e. interrogative “wh-” words (and accompanying auxiliary verbs) at the start of user queries.

    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
    my
    -0.06
    乐
    -0.06
    樂
    -0.06
     Alert
    -0.06
     Algebra
    -0.06
    prop
    -0.06
     palp
    -0.06
    .cwd
    -0.05
     ศร
    -0.05
    Aws
    -0.05
    POSITIVE LOGITS
     stagnant
    0.08
    implode
    0.07
    angu
    0.07
    ],&
    0.07
     obnov
    0.07
    duc
    0.07
     Больш
    0.06
    _zones
    0.06
     eternal
    0.06
     (%
    0.06
    Activations Density 0.035%

    No Known Activations