© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 37962
    Prev
    Next
    INDEX
    Explanations

    lists of information

    np_max-act · gemini-2.0-flash

    The neuron is triggered by tokens that are floating‐point numeric strings (i.e. numbers containing a decimal point).

    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
     login
    -0.07
    	Rect
    -0.06
     المت
    -0.06
     ビ
    -0.06
     정
    -0.06
     welcome
    -0.06
    ::.
    -0.06
    으로
    -0.06
    save
    -0.06
    codigo
    -0.06
    POSITIVE LOGITS
     programu
    0.08
     Basel
    0.07
    Validity
    0.07
     امتی
    0.07
    议
    0.07
    endencies
    0.07
    _VALID
    0.06
    _categoria
    0.06
    Italy
    0.06
    лючается
    0.06
    Activations Density 0.026%

    No Known Activations