© 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. 6388
    Prev
    Next
    INDEX
    Explanations

    statistical data

    np_max-act · gemini-2.0-flash

    The neuron is specialized for spotting numeric data—especially measurements, statistical values, and other number tokens (including decimals and percentages).

    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
    енными
    -0.07
    getMessage
    -0.06
     ngồi
    -0.06
     correspondent
    -0.06
    erais
    -0.06
     rises
    -0.06
    'on
    -0.06
    ो,
    -0.06
    呆
    -0.06
    anik
    -0.06
    POSITIVE LOGITS
    _src
    0.08
    _UUID
    0.07
     proves
    0.07
     CVE
    0.07
     trộn
    0.06
    $arr
    0.06
     ход
    0.06
     sop
    0.06
    .YEAR
    0.06
     Lad
    0.06
    Activations Density 0.022%

    No Known Activations