© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 125209
    Prev
    Next
    INDEX
    Explanations

    document fragments

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    アニメ
    -0.07
     TECH
    -0.07
     MOTOR
    -0.07
     Tutor
    -0.06
     halluc
    -0.06
     compression
    -0.06
     Atlas
    -0.06
    _byte
    -0.06
     �
    -0.06
    stats
    -0.06
    POSITIVE LOGITS
    _entities
    0.07
     forwards
    0.06
     toDate
    0.06
    .NonNull
    0.06
    شاء
    0.06
    rai
    0.06
    /connect
    0.06
     liabilities
    0.06
    Assert
    0.06
    债
    0.06
    Activations Density 1.110%

    No Known Activations