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

    Neuronpedia

    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. 13939
    Prev
    Next
    INDEX
    Explanations

    time

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect numerical time‐duration expressions (e.g. cooking or drying times).

    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
    <KeyValuePair
    -0.06
    θρώ
    -0.06
    AGER
    -0.06
    ("{
    -0.06
     арх
    -0.05
     VECTOR
    -0.05
    анні
    -0.05
     colour
    -0.05
    计划
    -0.05
     çeşit
    -0.05
    POSITIVE LOGITS
     starttime
    0.08
    operative
    0.08
    춘
    0.07
     คำ
    0.07
    StartTime
    0.07
    सम
    0.07
    میر
    0.07
    천
    0.07
    ibi
    0.07
    min
    0.07
    Activations Density 0.015%

    No Known Activations