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. 36258
    Prev
    Next
    INDEX
    Explanations

    code

    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
     duplic
    -0.07
    ected
    -0.06
     cog
    -0.06
     income
    -0.06
    .Controllers
    -0.06
     несколь
    -0.06
    .WriteLine
    -0.06
    /angular
    -0.06
     agar
    -0.06
     occurs
    -0.06
    POSITIVE LOGITS
     Admir
    0.06
     sugars
    0.06
    overn
    0.06
    ossal
    0.06
    (center
    0.06
    Number
    0.06
    ()
    ↵
    0.06
     вони
    0.06
    _extensions
    0.06
    体系
    0.06
    Activations Density 0.067%

    No Known Activations