© 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. 30438
    Prev
    Next
    INDEX
    Explanations

    Business actions/requests

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on mentions of user requests or tasks (e.g. “request,” “student work,” “user request”).

    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
     you
    -0.08
    animation
    -0.07
    You
    -0.07
    jte
    -0.06
    ffield
    -0.06
     disconnected
    -0.06
     microscopic
    -0.06
    you
    -0.06
    ();
    -0.06
     planets
    -0.06
    POSITIVE LOGITS
     должно
    0.08
    0.07
    .extract
    0.07
     وكانت
    0.06
    .allocate
    0.06
     ilişk
    0.06
     �
    0.06
    >--}}↵
    0.06
     decl
    0.06
    しており
    0.06
    Activations Density 0.166%

    No Known Activations