© 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. 65876
    Prev
    Next
    INDEX
    Explanations

    code and file configurations

    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
     Outputs
    -0.07
    Caption
    -0.06
     wsp
    -0.06
     newVal
    -0.06
    Exiting
    -0.06
    lamaktadır
    -0.06
    _Runtime
    -0.06
    획
    -0.06
     характериз
    -0.06
     Allocate
    -0.06
    POSITIVE LOGITS
    ство
    0.07
    大
    0.07
     پای
    0.07
    ;}↵↵
    0.06
    の人
    0.06
    にと
    0.06
     ;↵
    0.06
    кість
    0.06
    Marca
    0.06
     Jong
    0.06
    Activations Density 0.055%

    No Known Activations