© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 110204
    Prev
    Next
    INDEX
    Explanations

    song lyrics

    np_max-act · gemini-2.0-flash

    text related to children's nursery rhymes.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects occurrences of the proper-name phrase “Mary Mack” (i.e. the song title and its repeated use in the lyrics).

    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
     basal
    -0.07
    .Our
    -0.07
     غذایی
    -0.07
    λευτα
    -0.07
    (active
    -0.07
     tar
    -0.07
    enha
    -0.06
    .free
    -0.06
     Cant
    -0.06
     JW
    -0.06
    POSITIVE LOGITS
    <string
    0.07
    ров
    0.07
     dropdown
    0.06
    	sb
    0.06
     scrape
    0.06
     برگ
    0.06
     pueda
    0.06
    luv
    0.06
    ervices
    0.06
     пораж
    0.06
    Activations Density 0.074%

    No Known Activations