© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 25290
    Prev
    Next
    INDEX
    Explanations

    Informal online content

    np_max-act · gemini-2.0-flash

    The neuron detects first-person self-references (tokens like “I,” “I’m,” “I’ve,” 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
    ))))
    -0.07
     Craw
    -0.07
    }))
    -0.06
     midfielder
    -0.06
     밝
    -0.06
     dök
    -0.06
    SAFE
    -0.06
     upholstery
    -0.06
    imations
    -0.06
    ६
    -0.06
    POSITIVE LOGITS
     Once
    0.06
        ↵
    0.06
     hands
    0.06
    Text
    0.06
     pieces
    0.06
     coils
    0.06
     Overall
    0.06
     Constitutional
    0.06
    azes
    0.06
     principles
    0.06
    Activations Density 0.028%

    No Known Activations