© 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. 89792
    Prev
    Next
    INDEX
    Explanations

    Mixed text, numbers, names

    np_max-act · gemini-2.0-flash

    The neuron is a “list‐item” detector—it lights up on tokens that mark or appear in enumerations and lists (e.g. step numbers, numbered items, and list‐entry names).

    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
     başlan
    -0.07
     cables
    -0.07
     امر
    -0.06
    Apple
    -0.06
     Boulder
    -0.06
    914
    -0.06
     Apple
    -0.06
    unun
    -0.06
    Ice
    -0.06
    ulle
    -0.06
    POSITIVE LOGITS
    (by
    0.08
     dbc
    0.08
     Meghan
    0.07
    (argument
    0.07
     Attribute
    0.07
    .StylePriority
    0.07
     QPainter
    0.07
    .debug
    0.06
    (Text
    0.06
     QList
    0.06
    Activations Density 0.235%

    No Known Activations