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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 22284
    Prev
    Next
    INDEX
    Explanations

    autobiography/memoir

    np_max-act · gemini-2.0-flash

    specific references to autobiographical elements in people's lives.

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

    This neuron activates on mentions of a person’s written publications—e.g. “wrote,” “published,” “memoir,” “autobiography,” or book titles.

    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
    gran
    -0.07
    .age
    -0.07
     fruit
    -0.06
     ankle
    -0.06
     Sorted
    -0.06
    ặ
    -0.06
    roperties
    -0.06
    地球
    -0.06
    ži
    -0.06
    _manifest
    -0.06
    POSITIVE LOGITS
    BOOK
    0.08
     memoir
    0.07
     下跌
    0.07
    求购
    0.06
     dvě
    0.06
     ؟
    0.06
    주
    0.06
    نية
    0.06
     SAY
    0.06
     bye
    0.06
    Activations Density 0.017%

    No Known Activations