© 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. 12754
    Prev
    Next
    INDEX
    Explanations

    lists and keys

    np_max-act · gemini-2.0-flash

    This neuron detects the word “Key” when it appears as a section or table‐legend heading.

    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
     rapp
    -0.06
    wat
    -0.06
    .depart
    -0.06
    ::|
    -0.06
    $p
    -0.06
     résult
    -0.06
    _routes
    -0.06
    ーナ
    -0.06
     Мор
    -0.06
    撮
    -0.05
    POSITIVE LOGITS
    investment
    0.07
     Interface
    0.07
    Skin
    0.07
    stringLiteral
    0.07
    ापस
    0.07
     drive
    0.06
     INDEX
    0.06
    _typeDefinition
    0.06
     Searching
    0.06
    _RECE
    0.06
    Activations Density 0.002%

    No Known Activations