© 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. 6894
    Prev
    Next
    INDEX
    Explanations

    "["

    np_max-act · gemini-2.0-flash

    This neuron activates strongly on numeric literals (numbers) in code.

    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
    ammer
    -0.07
    .TEST
    -0.07
     Archie
    -0.07
    芳
    -0.07
    晶
    -0.07
    cura
    -0.07
     unpack
    -0.07
    혹
    -0.07
     Audi
    -0.07
    .date
    -0.07
    POSITIVE LOGITS
     mary
    0.06
    ско
    0.06
     连
    0.06
    {@
    0.06
    _↵↵
    0.06
    ([
    0.06
    ební
    0.06
    dney
    0.05
     daylight
    0.05
     yoktu
    0.05
    Activations Density 0.027%

    No Known Activations