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. 40664
    Prev
    Next
    INDEX
    Explanations

    public meetings

    np_max-act · gemini-2.0-flash

    This neuron detects personal-perspective references, especially first-person pronouns and related self-narrative language.

    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
     nik
    -0.08
    “Well
    -0.08
    TV
    -0.07
    Mana
    -0.07
     whatsapp
    -0.07
    tod
    -0.07
    两人
    -0.06
    elian
    -0.06
    File
    -0.06
    _person
    -0.06
    POSITIVE LOGITS
    @$
    0.07
     runoff
    0.07
    assertInstanceOf
    0.06
    540
    0.06
    .");
    ↵
    0.06
     '').
    0.06
     відкрит
    0.06
     penetration
    0.06
     Πολι
    0.06
     Assass
    0.06
    Activations Density 0.060%

    No Known Activations