© 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. 125932
    Prev
    Next
    INDEX
    Explanations

    compact

    np_max-act · gemini-2.0-flash

    This neuron activates on vehicle class or segment descriptors (e.g. “compact,” “mid-size,” “executive,” “sports,” “luxury,” “SUV,” “electric,” “hybrid”).

    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
    érc
    -0.07
     Royals
    -0.07
    лекс
    -0.07
    plex
    -0.06
     fug
    -0.06
     scrap
    -0.06
     painter
    -0.06
    attering
    -0.06
     bending
    -0.06
    dfa
    -0.06
    POSITIVE LOGITS
    ：<
    0.06
     GetName
    0.06
    +'&
    0.06
    cluster
    0.06
    (Spring
    0.06
     *
    0.06
     $('.
    0.06
    =in
    0.06
     accompanies
    0.06
     adore
    0.06
    Activations Density 0.022%

    No Known Activations