© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 544
    Prev
    Next
    INDEX
    Explanations

    abuse

    np_max-act · gemini-2.0-flash

    This neuron activates on the phrase “abused its discretion,” flagging instances of judicial “abuse of discretion.”

    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
    Fuck
    -0.07
    ::::::::::::::::
    -0.06
     registros
    -0.06
     shift
    -0.06
     shifted
    -0.06
     FEATURE
    -0.06
     noted
    -0.06
     tk
    -0.06
    Legendary
    -0.06
     Ruby
    -0.06
    POSITIVE LOGITS
    vetica
    0.07
    .await
    0.07
    гра
    0.07
    (join
    0.06
    .toArray
    0.06
    ную
    0.06
    DidLoad
    0.06
    MUX
    0.06
     Burma
    0.06
    ليات
    0.06
    Activations Density 0.001%

    No Known Activations