© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 79332
    Prev
    Next
    INDEX
    Explanations

    }

    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
    Ever
    -0.07
     Perry
    -0.06
     modelling
    -0.06
     Participation
    -0.06
    Pitch
    -0.06
     wired
    -0.06
    系
    -0.06
    anda
    -0.06
    гу
    -0.06
    processed
    -0.06
    POSITIVE LOGITS
    ateway
    0.07
     pozit
    0.07
     徒歩
    0.06
     Seks
    0.06
    .baidu
    0.06
     doen
    0.06
     BrowserAnimationsModule
    0.06
     χαρα
    0.06
    昭和
    0.06
     TMPro
    0.06
    Activations Density 0.017%

    No Known Activations