© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 89668
    Prev
    Next
    INDEX
    Explanations

    Questions/requests in online forums

    np_max-act · gemini-2.0-flash

    This neuron responds to user instructions phrased in the first person or containing imperatives (e.g. “I,” “send,” “then,” “you”).

    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
     renters
    -0.07
     Russo
    -0.06
    าะห
    -0.06
    -support
    -0.06
    arcy
    -0.06
    ophysical
    -0.06
    aptcha
    -0.06
    _greater
    -0.06
     milfs
    -0.06
     heading
    -0.06
    POSITIVE LOGITS
    àng
    0.07
     seiz
    0.07
     Script
    0.07
    _else
    0.07
     aktual
    0.07
     �
    0.07
     týden
    0.07
     برابر
    0.06
     boilers
    0.06
     aquí
    0.06
    Activations Density 0.039%

    No Known Activations