© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 80101
    Prev
    Next
    INDEX
    Explanations

    the

    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
    _input
    -0.07
    免
    -0.07
     refused
    -0.07
    strain
    -0.07
    }).
    -0.07
    _mem
    -0.07
    ана
    -0.07
     rewarding
    -0.06
    .EventSystems
    -0.06
    	direction
    -0.06
    POSITIVE LOGITS
     phenomen
    0.07
    .lo
    0.06
     аж
    0.06
    /support
    0.06
    ный
    0.06
    "sync
    0.06
     includ
    0.06
     pale
    0.06
     кількість
    0.06
    ử
    0.06
    Activations Density 0.048%

    No Known Activations