© 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. 11-RESID-POST-AA
    6. 25773
    Prev
    Next
    INDEX
    Explanations

    accurate

    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
     Parses
    -0.07
    中國
    -0.07
    sınız
    -0.07
    _delete
    -0.07
     persever
    -0.06
    -core
    -0.06
    ATRIX
    -0.06
    eyse
    -0.06
    zell
    -0.06
    _CREATE
    -0.06
    POSITIVE LOGITS
    RNA
    0.06
     redhead
    0.06
    Temperature
    0.06
    Eta
    0.06
    ©
    0.06
     يم
    0.05
    %f
    0.05
     ERA
    0.05
     não
    0.05
     Quinn
    0.05
    Activations Density 0.125%

    No Known Activations