© 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. 68581
    Prev
    Next
    INDEX
    Explanations

    sentence starters

    np_max-act · gemini-2.0-flash

    The neuron fires on sentences opening with lead‐in pronouns or existential constructions—i.e. “We” or “There” at the start of background/introductory statements.

    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
    нюю
    -0.07
    ιστο
    -0.06
    remain
    -0.06
     kazanç
    -0.06
    faculty
    -0.06
    Histor
    -0.06
    oha
    -0.06
    cxx
    -0.06
     CPL
    -0.06
     이러한
    -0.06
    POSITIVE LOGITS
     Sanchez
    0.07
     mapped
    0.07
    ánchez
    0.06
    "${
    0.06
    xfff
    0.06
     Submit
    0.06
    (F
    0.06
     recreational
    0.06
    (Map
    0.06
    ";
    0.06
    Activations Density 0.012%

    No Known Activations