© 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. 44619
    Prev
    Next
    INDEX
    Explanations

    mathematical bounds are tight/optimal

    np_max-act · gemini-2.0-flash

    The neuron responds to numeric constants, especially floating-point or decimal numbers appearing 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
     AV
    -0.07
     recipro
    -0.06
    ometry
    -0.06
    خراج
    -0.06
     میل
    -0.06
    reated
    -0.06
    Factory
    -0.06
    Detector
    -0.06
    (h
    -0.06
    از
    -0.06
    POSITIVE LOGITS
    诗
    0.07
    �
    0.07
     몽
    0.07
    ĩa
    0.06
    lisi
    0.06
    .rev
    0.06
        ↵    ↵    ↵    ↵
    0.06
    zą
    0.06
     swiper
    0.06
     Karel
    0.06
    Activations Density 0.017%

    No Known Activations