© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 6161
    Prev
    Next
    INDEX
    Explanations

    step

    np_max-act · gemini-2.0-flash

    This neuron activates on the word “repeat” (and its variants like “repita”) when used in step‐by‐step instructions to tell the user to repeat a range of steps.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    instructions or queries related to manipulating data within programming or database environments.

    oai_token-act-pair · gpt-4o-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
     зобов
    -0.07
     آنچه
    -0.06
    つぶ
    -0.06
    自身
    -0.06
     色
    -0.06
     ammonia
    -0.06
    ίος
    -0.06
    ιστο
    -0.06
     другим
    -0.06
    CheckedChangeListener
    -0.06
    POSITIVE LOGITS
    nbsp
    0.07
     dataIndex
    0.07
     cup
    0.06
     kg
    0.06
    oreal
    0.06
    .Set
    0.06
     Mining
    0.06
    encia
    0.06
    óz
    0.06
     volley
    0.06
    Activations Density 0.006%

    No Known Activations