Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 43544
    Prev
    Next
    INDEX
    Explanations

    Movie credits

    np_max-act · gemini-2.0-flash

    The neuron activates on capitalized proper‐noun tokens—names of people and titles—in cast lists and filmography entries.

    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
     wget
    -0.07
     Bent
    -0.07
    RAM
    -0.06
     Lic
    -0.06
     наві
    -0.06
    eceği
    -0.06
    _By
    -0.06
    วรร
    -0.06
    eryl
    -0.06
     بالرياض
    -0.06
    POSITIVE LOGITS
    ograf
    0.07
    .grad
    0.07
    قام
    0.06
    stüt
    0.06
     Fragment
    0.06
    Updater
    0.06
    _SIZE
    0.06
     Responses
    0.06
    筑
    0.06
    …”
    0.06
    Activations Density 0.024%

    No Known Activations