Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 79721
    Prev
    Next
    INDEX
    Explanations

    Acronyms or initialisms

    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
    ,该
    -0.07
     FAST
    -0.07
    .firstname
    -0.07
     pager
    -0.06
    .addTab
    -0.06
    HIGH
    -0.06
     remembering
    -0.06
    .setSelection
    -0.06
     Εκ
    -0.06
     взгляд
    -0.06
    POSITIVE LOGITS
     Christianity
    0.07
    LOS
    0.06
    ObjectOfType
    0.06
    refs
    0.06
     mie
    0.06
     qualifiers
    0.06
     ◑
    0.06
    Issues
    0.06
    틱
    0.06
     GetValue
    0.06
    Activations Density 0.069%

    No Known Activations