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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 41521
    Prev
    Next
    INDEX
    Explanations

    (new

    np_max-act · gemini-2.0-flash

    The neuron is triggered by German-language words or word fragments.

    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
     gim
    -0.07
     stretches
    -0.07
    _glob
    -0.07
    sız
    -0.06
    ποί
    -0.06
    ATTER
    -0.06
     dijital
    -0.06
    余
    -0.06
    .Question
    -0.06
     lifecycle
    -0.06
    POSITIVE LOGITS
    .Pixel
    0.07
    λλη
    0.07
    $options
    0.07
    acles
    0.06
    (Dense
    0.06
     upgraded
    0.06
     вис
    0.06
     fark
    0.06
     CHtml
    0.06
    escaping
    0.06
    Activations Density 0.080%

    No Known Activations