© 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. 11-RESID-POST-AA
    11. 36707
    Prev
    Next
    INDEX
    Explanations

    this

    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
    eworthy
    -0.06
     최신
    -0.06
     MongoClient
    -0.06
    PDO
    -0.06
    _HEALTH
    -0.06
     innate
    -0.05
    Device
    -0.05
    PasswordEncoder
    -0.05
    NoArgsConstructor
    -0.05
    culo
    -0.05
    POSITIVE LOGITS
    牧
    0.07
     Rentals
    0.07
     علاوه
    0.07
     который
    0.07
     accommodate
    0.07
    ENABLE
    0.06
     cop
    0.06
    алась
    0.06
     encore
    0.06
    ）：
    0.06
    Activations Density 0.057%

    No Known Activations