© 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. 55591
    Prev
    Next
    INDEX
    Explanations

    `

    np_max-act · gemini-2.0-flash

    Python code related to database creation using SQLAlchemy.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron is detecting package installation commands (e.g. “pip install …”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    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
     güney
    -0.08
    [number
    -0.08
    ấn
    -0.07
    (each
    -0.07
     Documents
    -0.07
     NG
    -0.07
     Entwicklung
    -0.07
     payloads
    -0.07
     resent
    -0.06
    ................................................................
    -0.06
    POSITIVE LOGITS
    agement
    0.06
     Gavin
    0.06
     familia
    0.06
    ormap
    0.06
     PodsDummy
    0.06
     »↵↵
    0.06
    materials
    0.06
    0.06
     Texas
    0.06
    roleId
    0.05
    Activations Density 0.034%

    No Known Activations