© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 59219
    Prev
    Next
    INDEX
    Explanations

    ucer

    np_max-act · gemini-2.0-flash

    This neuron fires on occurrences of “Fox” (e.g. the Fox Broadcasting Company), i.e. it detects mentions of the Fox network.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    CB
    -0.07
    рад
    -0.06
    ��
    -0.06
    caa
    -0.06
    court
    -0.06
    립
    -0.06
    몬
    -0.06
    chu
    -0.06
     aan
    -0.06
    ulating
    -0.06
    POSITIVE LOGITS
    宇
    0.07
    []=$
    0.07
    -price
    0.06
    _ne
    0.06
     později
    0.06
     olduğ
    0.06
     quantidade
    0.06
     grandchildren
    0.06
    顺
    0.06
    體
    0.06
    Activations Density 0.292%

    No Known Activations