© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 59375
    Prev
    Next
    INDEX
    Explanations

    mention

    np_max-act · gemini-2.0-flash

    conversational and interactive phrases or elements commonly used in dialogue.

    oai_token-act-pair · gpt-4o-mini
    Triggered by @xinyanhu8

    The neuron detects self-referential parenthetical asides where the speaker signals they “forgot to mention” something.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    (H
    -0.08
    ょ
    -0.07
    Min
    -0.07
     Ethernet
    -0.07
    {↵↵
    -0.06
    م
    -0.06
     Blond
    -0.06
    iage
    -0.06
     {}
↵
↵
    -0.06
    Auth
    -0.06
    POSITIVE LOGITS
     onun
    0.07
    vere
    0.06
     così
    0.06
    .oauth
    0.06
    tmpl
    0.06
    starts
    0.06
     geopol
    0.06
     �
    0.06
     quiero
    0.06
     Über
    0.06
    Activations Density 0.028%

    No Known Activations