© 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. 41574
    Prev
    Next
    INDEX
    Explanations

    case

    np_max-act · gemini-2.0-flash

    This neuron consistently activates on the word “case” (and its plural/forms) in contexts like “case–control study,” i.e. mentions of “case” in case‐control study descriptions.

    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
    cker
    -0.07
    CKER
    -0.07
     denied
    -0.07
     ovarian
    -0.06
    >({
    -0.06
    Objects
    -0.06
     Ability
    -0.06
    ihilation
    -0.06
     Reflex
    -0.06
    Identifier
    -0.06
    POSITIVE LOGITS
    _typeDefinition
    0.08
    .sourceforge
    0.07
    .Nav
    0.07
    �认
    0.07
     ComponentFixture
    0.07
     zástup
    0.06
    .navigation
    0.06
     prům
    0.06
     totaling
    0.06
     Nz
    0.06
    Activations Density 0.009%

    No Known Activations