© 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. 49892
    Prev
    Next
    INDEX
    Explanations

    ast

    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
     MOS
    -0.07
     Snow
    -0.07
     George
    -0.07
    (ns
    -0.06
     dubna
    -0.06
    atty
    -0.06
     theme
    -0.06
     Legs
    -0.06
    Foreground
    -0.06
     Greenland
    -0.06
    POSITIVE LOGITS
     onder
    0.07
    commit
    0.07
     области
    0.06
    是否
    0.06
    _AUT
    0.06
    ματος
    0.06
     começ
    0.06
    회사
    0.06
     lookahead
    0.06
    фектив
    0.06
    Activations Density 0.002%

    No Known Activations