© 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. 25948
    Prev
    Next
    INDEX
    Explanations

    business and management concepts

    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
     hava
    -0.07
    	save
    -0.07
     Ezra
    -0.06
    wart
    -0.06
     bath
    -0.06
    emek
    -0.06
    _bt
    -0.06
     Typically
    -0.06
    メージ
    -0.06
    Mutex
    -0.06
    POSITIVE LOGITS
    \modules
    0.06
     нас
    0.06
    .ViewHolder
    0.06
    .Roles
    0.06
     acciones
    0.06
    _NON
    0.06
    seq
    0.06
     elapsedTime
    0.06
    ),
    0.06
    pany
    0.06
    Activations Density 0.142%

    No Known Activations