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. 1005
    Prev
    Next
    INDEX
    Explanations

    Choices and self-determination

    np_max-act · gemini-2.0-flash

    The neuron responds to language about personal agency—terms and phrases that emphasize choosing, responsibility, and taking control of one’s actions.

    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
     clustering
    -0.07
     Dialogue
    -0.06
     possessed
    -0.06
     Bever
    -0.06
    auf
    -0.06
     fucked
    -0.06
    root
    -0.06
    -ret
    -0.06
    形
    -0.06
    Discover
    -0.06
    POSITIVE LOGITS
    ้าอ
    0.08
    pth
    0.07
    _FIELD
    0.07
    John
    0.06
    احی
    0.06
    :@"%
    0.06
    (gray
    0.06
    eşil
    0.06
    (tab
    0.06
     ای
    0.06
    Activations Density 0.028%

    No Known Activations