© 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. 7-RESID-POST-AA
    11. 53907
    Prev
    Next
    INDEX
    Explanations

    self-reference

    np_max-act · gemini-2.0-flash

    tokens that form self-referential words (like "self", "se stesso", "si misma", "me stesso") — i.e., mentions of the self or oneself.

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tấn
    -0.07
    LatLng
    -0.06
    并不
    -0.06
    亿
    -0.06
    اول
    -0.06
    的是
    -0.06
     在
    -0.06
     revenue
    -0.06
    那样
    -0.06
    HOOK
    -0.06
    POSITIVE LOGITS
    Transfer
    0.07
     поверхности
    0.07
     enemy
    0.07
    .Roles
    0.06
     tun
    0.06
     آزمایش
    0.06
     docs
    0.06
     puerto
    0.06
     Well
    0.06
    amon
    0.06
    Activations Density 0.029%

    No Known Activations