© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 126758
    Prev
    Next
    INDEX
    Explanations

    N

    np_max-act · gemini-2.0-flash

    This neuron detects the header line “U.S. COURT OF APPEALS FOR THE NINTH CIRCUIT,” i.e. the official court‐name tokens at the top of the document.

    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
     Bernard
    -0.07
    xFFFFFFFF
    -0.07
    Snake
    -0.07
     Felix
    -0.07
    Vector
    -0.07
    _collect
    -0.07
     mtx
    -0.07
     Loren
    -0.07
    \Collections
    -0.06
     Roberto
    -0.06
    POSITIVE LOGITS
    .createStatement
    0.06
    _front
    0.06
     Lagos
    0.06
     questioning
    0.06
     inhab
    0.06
    ровер
    0.06
    (datetime
    0.06
    TOR
    0.06
    	GPIO
    0.06
     exig
    0.06
    Activations Density 0.011%

    No Known Activations