Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 1039
    Prev
    Next
    INDEX
    Explanations

    experiences

    np_max-act · gemini-2.0-flash

    This neuron detects marketing-style “once you try X, you’ll never go back” promotional phrasing.

    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
     simulator
    -0.08
     identical
    -0.07
    .state
    -0.07
    _item
    -0.06
     başında
    -0.06
     RTP
    -0.06
     interior
    -0.06
    ButtonItem
    -0.06
    TextColor
    -0.06
     تنها
    -0.06
    POSITIVE LOGITS
     参考
    0.07
     depressive
    0.06
    uestion
    0.06
    ง
    0.06
     ERR
    0.06
    rch
    0.06
    .Title
    0.06
    ota
    0.06
    fx
    0.06
    ünk
    0.06
    Activations Density 0.110%

    No Known Activations