Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 78942
    Prev
    Next
    INDEX
    Explanations

    struct

    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
    eah
    -0.07
    Ap
    -0.06
    代理
    -0.06
     dny
    -0.06
    <AM
    -0.06
    //------------------------------------------------------------------------------------------------
    -0.06
    _here
    -0.06
    INU
    -0.06
     fileType
    -0.06
    _rs
    -0.06
    POSITIVE LOGITS
     prepend
    0.07
    hips
    0.07
     represents
    0.06
     taller
    0.06
    βε
    0.06
     earn
    0.06
     target
    0.06
     wrench
    0.06
     INSERT
    0.06
    нима
    0.06
    Activations Density 0.004%

    No Known Activations