© 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 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. 57053
    Prev
    Next
    INDEX
    Explanations

    siblings

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of family‐relationship terms.

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

    relationships and ages within familial contexts.

    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
     apparel
    -0.07
     septembre
    -0.06
    PRE
    -0.06
     Kitty
    -0.06
     barrel
    -0.06
     lettre
    -0.06
    ceans
    -0.06
     Furthermore
    -0.06
     />↵
    -0.06
     swapped
    -0.06
    POSITIVE LOGITS
    .wik
    0.07
     willing
    0.06
     однов
    0.06
     jinak
    0.06
    _asc
    0.06
     anomaly
    0.06
    .Criteria
    0.06
    .numpy
    0.06
     advers
    0.06
    .flush
    0.06
    Activations Density 0.022%

    No Known Activations