© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 55543
    Prev
    Next
    INDEX
    Explanations

    There

    np_max-act · gemini-2.0-flash

    The neuron detects quantitative data—especially decimal‐style numbers, measurements, percentages, and statistical values like P-values.

    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
     squares
    -0.07
    CORE
    -0.07
    White
    -0.06
    (dictionary
    -0.06
     pozor
    -0.06
    .exception
    -0.06
    UNICATION
    -0.06
    ात
    -0.06
    两个
    -0.06
    (token
    -0.06
    POSITIVE LOGITS
     Barcl
    0.07
    claim
    0.07
     سی
    0.06
    _FINISH
    0.06
     floatValue
    0.06
     Нет
    0.06
     فی
    0.06
     hiss
    0.06
     Qué
    0.06
     dared
    0.06
    Activations Density 0.094%

    No Known Activations