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. 53456
    Prev
    Next
    INDEX
    Explanations

    European history/names

    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
    uffs
    -0.06
    贵
    -0.06
    ورت
    -0.06
     worms
    -0.06
     ecosystem
    -0.06
     lied
    -0.06
    Permissions
    -0.06
     Listen
    -0.06
     شکن
    -0.06
    Ut
    -0.06
    POSITIVE LOGITS
    /tasks
    0.07
    abeth
    0.07
    ?
    0.06
    κρα
    0.06
    habit
    0.06
    Franc
    0.06
     Exec
    0.06
    .&
    0.06
     Henri
    0.06
     Sylv
    0.06
    Activations Density 0.042%

    No Known Activations