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

    Neuronpedia

    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. 7594
    Prev
    Next
    INDEX
    Explanations

    introduction of names

    np_max-act · gemini-2.0-flash

    This neuron responds to the placeholder tokens “NAME” (and its indexed variants), i.e. character‐name placeholders.

    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
     pulmonary
    -0.06
     Pluto
    -0.06
    Handler
    -0.06
    _decoder
    -0.06
    เกาะ
    -0.06
     QUEST
    -0.06
     Got
    -0.06
    Postal
    -0.06
     Bodies
    -0.06
    PosX
    -0.06
    POSITIVE LOGITS
    "W
    0.07
    [L
    0.07
    ."""
    0.07
    "L
    0.06
    "C
    0.06
    dex
    0.06
    wc
    0.06
     ------------
    0.06
    ,“
    0.06
     dll
    0.06
    Activations Density 0.076%

    No Known Activations