© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 41604
    Prev
    Next
    INDEX
    Explanations

    register

    np_max-act · gemini-2.0-flash

    This neuron fires on calls-to-action encouraging users to register or sign up (often phrased as “register for free” or “sign up”) on a forum or site.

    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
     filmpjes
    -0.07
    fix
    -0.07
    فی
    -0.07
     розпов
    -0.06
     大阪
    -0.06
     دارند
    -0.06
    _videos
    -0.06
    urban
    -0.06
    _FORM
    -0.06
    loit
    -0.06
    POSITIVE LOGITS
     clandest
    0.07
     liquidity
    0.07
     神马收录
    0.07
    ResourceManager
    0.06
    qw
    0.06
    Pixmap
    0.06
    .QRect
    0.06
    odium
    0.06
     hunted
    0.06
    lopen
    0.06
    Activations Density 0.005%

    No Known Activations