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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 12875
    Prev
    Next
    INDEX
    Explanations

    model

    np_max-act · gemini-2.0-flash

    The neuron fires on self-referential disclaimers where the assistant describes itself as a “modelo de lenguaje” (e.g., “como modelo de lenguaje…”).

    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
    avors
    -0.07
    (n
    -0.06
    ktop
    -0.06
     pé
    -0.06
    046
    -0.06
     objective
    -0.06
    -ip
    -0.06
    natal
    -0.06
    726
    -0.06
    (ip
    -0.06
    POSITIVE LOGITS
     çift
    0.07
    。</
    0.07
    gulp
    0.06
     Ladies
    0.06
     File
    0.06
    caption
    0.06
     chinese
    0.06
    ичні
    0.06
    資料
    0.06
    )。↵
    0.06
    Activations Density 0.008%

    No Known Activations