Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 126516
    Prev
    Next
    INDEX
    Explanations

    coworking spaces

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of flexible or shared office/workspace concepts (e.g., “co-working,” “spaces,” “workspace,” “shared office”).

    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
     Injector
    -0.07
    964
    -0.06
    альна
    -0.06
    運動
    -0.06
     workshop
    -0.06
     Ně
    -0.06
    (and
    -0.06
    274
    -0.06
    体系
    -0.06
     neglected
    -0.06
    POSITIVE LOGITS
    steel
    0.06
    categoria
    0.06
     همه
    0.06
     společnosti
    0.06
    LANGUAGE
    0.06
     preserve
    0.06
    jar
    0.06
    Header
    0.06
     LoginComponent
    0.06
     проект
    0.06
    Activations Density 0.013%

    No Known Activations