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. 86131
    Prev
    Next
    INDEX
    Explanations

    Informal discussions

    np_max-act · gemini-2.0-flash

    This neuron fires on self-referential and conversational pronouns and response markers (e.g. I, we, you, thanks, appears) in comment replies.

    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
    MH
    -0.07
    arl
    -0.06
    rides
    -0.06
     male
    -0.06
    pios
    -0.06
    essa
    -0.06
    borough
    -0.06
     sns
    -0.06
    (outputs
    -0.06
    essed
    -0.06
    POSITIVE LOGITS
    .GridColumn
    0.07
     diminish
    0.06
     GPI
    0.06
    费
    0.06
    …and
    0.06
    |int
    0.06
     сы
    0.06
     삼성
    0.06
    .Scope
    0.06
    !/
    0.06
    Activations Density 0.046%

    No Known Activations