© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 125983
    Prev
    Next
    INDEX
    Explanations

    Lists of names

    np_max-act · gemini-2.0-flash

    The neuron primarily activates on personal names (i.e. individual people’s names).

    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
     page
    -0.07
    Maybe
    -0.06
    ingredient
    -0.06
    .land
    -0.06
    (events
    -0.06
     Libyan
    -0.06
     cita
    -0.06
    -energy
    -0.06
    站在
    -0.06
     Max
    -0.06
    POSITIVE LOGITS
    ्प
    0.07
     Bh
    0.07
     Gandhi
    0.07
     Sharma
    0.07
    .entrySet
    0.07
     celkem
    0.07
     Delhi
    0.07
    hma
    0.06
     Gujar
    0.06
     bh
    0.06
    Activations Density 0.082%

    No Known Activations