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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 40657
    Prev
    Next
    INDEX
    Explanations

    Personal narratives/dialogue

    np_max-act · gemini-2.0-flash

    This neuron fires on first‐person pronouns (like “I,” “me,” “my”) when the text is about the speaker’s own feelings or 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
    aware
    -0.07
     SEM
    -0.07
    .WinControls
    -0.07
    ()).
    -0.07
    closure
    -0.06
    Receive
    -0.06
    Plate
    -0.06
     Exchange
    -0.06
     Wait
    -0.06
    rg
    -0.06
    POSITIVE LOGITS
    _predicted
    0.06
     prayed
    0.06
    azu
    0.06
    різ
    0.06
    �
    0.06
    bv
    0.06
    .','
    0.06
     معل
    0.05
    ','
    0.05
    istribute
    0.05
    Activations Density 0.067%

    No Known Activations