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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 57928
    Prev
    Next
    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash

    The neuron fires on connective words that specify itinerary directives—terms like “starting,” “ending,” “with,” “in,” and “and” that introduce travel‐plan parameters.

    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
    кому
    -0.07
     Gord
    -0.07
     meth
    -0.06
     became
    -0.06
     metabol
    -0.06
    验证码
    -0.06
    _MetaData
    -0.06
    Christ
    -0.06
    以来
    -0.06
    이며
    -0.06
    POSITIVE LOGITS
    _po
    0.07
    üyle
    0.06
     Biol
    0.06
    しゃ
    0.06
     탈
    0.06
     tez
    0.06
     UD
    0.06
    _wrap
    0.06
     substantially
    0.06
     MySql
    0.06
    Activations Density 0.048%

    No Known Activations