© 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. 129620
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron activates on the quoted command identifiers (e.g. “google”, “browse_website”, “start_agent”)—in other words, it spots the names of commands enclosed in double quotes.

    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
     nen
    -0.06
     Easter
    -0.06
     Movies
    -0.06
     خلق
    -0.06
    <Texture
    -0.06
    .offer
    -0.06
    atest
    -0.06
     German
    -0.06
     Daly
    -0.06
    Fu
    -0.06
    POSITIVE LOGITS
     Aires
    0.06
     accordance
    0.06
    ливий
    0.06
     guit
    0.06
    ENABLE
    0.06
    entin
    0.06
    .ACTION
    0.06
    ificados
    0.06
     Break
    0.06
     Beckham
    0.06
    Activations Density 0.004%

    No Known Activations