© 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
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 168
    Prev
    Next
    INDEX
    Explanations

    (

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fcc
    -0.07
     ability
    -0.07
    ़त
    -0.06
     Kirk
    -0.06
     gấp
    -0.06
     UIImagePickerController
    -0.06
    銀
    -0.06
     orc
    -0.06
     MEMORY
    -0.06
     irgend
    -0.06
    POSITIVE LOGITS
    /javascript
    0.07
    .Value
    0.07
     tóc
    0.07
    rot
    0.06
    救
    0.06
    Validators
    0.06
     disadvantaged
    0.06
    /Set
    0.06
    (WebDriver
    0.06
     Modelo
    0.06
    Activations Density 0.057%

    No Known Activations