© 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. 124788
    Prev
    Next
    INDEX
    Explanations

    match

    np_max-act · gemini-2.0-flash

    This neuron activates on verbs and phrases that describe matching or connecting people (e.g. match, finding, connect).

    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
    Behaviour
    -0.08
    -project
    -0.08
    perfil
    -0.08
     sacrifices
    -0.07
    uploads
    -0.07
    036
    -0.07
     requesting
    -0.07
    Profiles
    -0.07
    959
    -0.07
     vidéo
    -0.07
    POSITIVE LOGITS
     matched
    0.07
     istedi
    0.06
     ACC
    0.06
    >Welcome
    0.06
     outright
    0.06
     минут
    0.06
    Come
    0.06
     mắc
    0.06
     işi
    0.06
    (LL
    0.06
    Activations Density 0.009%

    No Known Activations