© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 58295
    Prev
    Next
    INDEX
    Explanations

    Online chat/forum posts

    np_max-act · gemini-2.0-flash

    It detects first-person references (I/me/my) especially when used in questions or requests for help.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
    redients
    -0.07
    .elements
    -0.07
     усі
    -0.06
     території
    -0.06
    andy
    -0.06
    _chg
    -0.06
    ほ
    -0.06
    ancement
    -0.06
    abei
    -0.06
    atted
    -0.06
    POSITIVE LOGITS
     ]]↵
    0.07
    (..
    0.06
     learner
    0.06
    (Seq
    0.06
    organic
    0.06
    ACION
    0.06
    ılığ
    0.06
    //{{
    0.06
    RoutingModule
    0.06
     Img
    0.06
    Activations Density 0.628%

    No Known Activations