© 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. 11-RESID-POST-AA
    6. 78200
    Prev
    Next
    INDEX
    Explanations

    onc

    np_max-act · gemini-2.0-flash
    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
     mData
    -0.07
    (Properties
    -0.06
    having
    -0.06
    .Fail
    -0.06
     fail
    -0.06
     barely
    -0.06
    distinct
    -0.06
    574
    -0.06
     waar
    -0.06
    파일
    -0.06
    POSITIVE LOGITS
     onc
    0.14
     Onc
    0.10
    orů
    0.07
    onte
    0.07
    ológ
    0.07
    LinkedIn
    0.07
    lol
    0.07
     University
    0.07
    Outlined
    0.07
    PickerController
    0.07
    Activations Density 0.002%

    No Known Activations