© 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. 8980
    Prev
    Next
    INDEX
    Explanations

    Section divider

    np_max-act · gemini-2.0-flash

    This neuron detects long runs of punctuation (especially repeated dashes or similar characters) used as section or formatting separators in the text.

    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
     ابت
    -0.07
     WORK
    -0.06
     toplum
    -0.06
    (tolua
    -0.06
     удоб
    -0.06
     returnType
    -0.06
    .ReadInt
    -0.06
     občan
    -0.06
    (red
    -0.06
     dbHelper
    -0.06
    POSITIVE LOGITS
    tz
    0.07
    -
    0.07
    Cheap
    0.07
    sizes
    0.07
    ures
    0.07
    -h
    0.07
    --
    0.07
    ruary
    0.07
    lıkları
    0.06
    -visible
    0.06
    Activations Density 0.003%

    No Known Activations