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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 77433
    Prev
    Next
    INDEX
    Explanations

    CD

    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
    ANNER
    -0.08
    라마
    -0.08
    啊啊
    -0.07
     Banks
    -0.07
     Parker
    -0.07
    branch
    -0.07
    @interface
    -0.07
     Root
    -0.07
     METHOD
    -0.07
     Blow
    -0.07
    POSITIVE LOGITS
     CDs
    0.10
     CD
    0.09
     fatalError
    0.06
     cosy
    0.06
    CD
    0.06
    ичного
    0.06
     AdapterView
    0.06
     CDN
    0.06
    odka
    0.06
    Δ
    0.06
    Activations Density 0.003%

    No Known Activations