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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 102812
    Prev
    Next
    INDEX
    Explanations

    Narratives about people

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect German age‐expression tokens (e.g. number plus “-jährige/-jährig” constructions).

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

    dialogues involving interactions between characters in a social or romantic context.

    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
     ADD
    -0.06
    .mb
    -0.06
    iti
    -0.06
    inke
    -0.06
     Dropbox
    -0.06
     rent
    -0.06
     URL
    -0.06
    MET
    -0.06
    ((-
    -0.06
    028
    -0.06
    POSITIVE LOGITS
     reassure
    0.07
    يدا
    0.07
    vehicles
    0.07
     yardımcı
    0.07
    IRC
    0.07
    _shuffle
    0.07
     reassuring
    0.06
    tal
    0.06
    ا
    0.06
    ασία
    0.06
    Activations Density 0.007%

    No Known Activations