© 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. 80030
    Prev
    Next
    INDEX
    Explanations

    trade

    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
     dall
    -0.07
    .SerializeObject
    -0.06
     veniam
    -0.06
     above
    -0.06
    稿
    -0.06
    iore
    -0.06
    villa
    -0.06
    dığı
    -0.05
    ondere
    -0.05
    ezi
    -0.05
    POSITIVE LOGITS
    FileChooser
    0.07
     twentieth
    0.07
    ","",
    0.07
     incumb
    0.07
    言
    0.06
    [++
    0.06
    �이
    0.06
     Fuk
    0.06
    Added
    0.06
     malé
    0.06
    Activations Density 0.012%

    No Known Activations