© 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. 6465
    Prev
    Next
    INDEX
    Explanations

    legal/administrative decisions

    np_max-act · gemini-2.0-flash

    This neuron responds to specialized medical-vocational terminology and references to guidelines (e.g., “medical,” “vocational,” “guidelines,” “grids,” “evidence,” “RFC”).

    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
    .not
    -0.07
     crib
    -0.07
     DropIndex
    -0.07
    edio
    -0.07
     mois
    -0.06
    (done
    -0.06
    Ted
    -0.06
    .bid
    -0.06
    ($_
    -0.06
    bid
    -0.06
    POSITIVE LOGITS
    _CART
    0.06
     suggestions
    0.06
    科技
    0.06
     HOW
    0.06
     Tro
    0.06
    áků
    0.06
    兵
    0.06
    block
    0.06
    built
    0.06
     customizable
    0.06
    Activations Density 0.004%

    No Known Activations