© 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. 89428
    Prev
    Next
    INDEX
    Explanations

    position

    np_max-act · gemini-2.0-flash

    The neuron fires most strongly on words that describe physically placing or positioning oneself or something (e.g. “positioning,” “inside,” “between”).

    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
     known
    -0.07
     Rabbit
    -0.06
     prosecuting
    -0.06
     plaintiff
    -0.06
    Rendering
    -0.06
     payments
    -0.06
     strcat
    -0.06
    检查
    -0.06
     fø
    -0.06
    畫
    -0.06
    POSITIVE LOGITS
     positioned
    0.08
    їна
    0.08
    AGED
    0.08
     staging
    0.07
    ísto
    0.07
    设置
    0.07
    -options
    0.07
     teď
    0.07
    ARK
    0.07
    тин
    0.06
    Activations Density 0.015%

    No Known Activations