© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 126757
    Prev
    Next
    INDEX
    Explanations

    academic texts

    np_max-act · gemini-2.0-flash

    This neuron detects numerical data and statistical measurements (e.g. percentages, decimal values, counts) 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
    secured
    -0.07
    .localized
    -0.06
    (todo
    -0.06
     موقع
    -0.06
     completion
    -0.06
    .record
    -0.06
    पन
    -0.06
     pBuffer
    -0.06
    指导
    -0.06
    وم
    -0.06
    POSITIVE LOGITS
    rescia
    0.08
    enght
    0.07
     Catalonia
    0.07
     lenght
    0.07
     carried
    0.07
     degli
    0.06
    äng
    0.06
     prefab
    0.06
    nými
    0.06
     financed
    0.06
    Activations Density 0.777%

    No Known Activations