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. 90094
    Prev
    Next
    INDEX
    Explanations

    self-reference

    np_max-act · gemini-2.0-flash

    The neuron fires on first-person self-references and introductions (e.g. “I,” “me,” “my,” “we,” “my name is,” etc.).

    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
    .endTime
    -0.07
     Rubio
    -0.06
    .Dispose
    -0.06
    .**************↵
    -0.06
    ysl
    -0.06
    _big
    -0.06
     bezier
    -0.06
    (visible
    -0.06
    _rows
    -0.06
     end
    -0.06
    POSITIVE LOGITS
    сти
    0.08
    loe
    0.07
    ौट
    0.07
    ımızı
    0.07
    -built
    0.07
    нимает
    0.07
    ね
    0.06
     autistic
    0.06
    нах
    0.06
    uido
    0.06
    Activations Density 0.038%

    No Known Activations