© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 12599
    Prev
    Next
    INDEX
    Explanations

    introductions

    np_max-act · gemini-2.0-flash

    The neuron spotlights first-person self-references—especially the pronoun “I” (and its contractions) when stating personal facts or experiences.

    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
    _Delete
    -0.06
     따른
    -0.06
    _SP
    -0.06
    !!↵↵
    -0.06
     Jord
    -0.06
               
    -0.06
     QC
    -0.06
    func
    -0.06
    Initializing
    -0.06
    Want
    -0.06
    POSITIVE LOGITS
     może
    0.07
    uali
    0.07
    
    0.06
    Verifier
    0.06
     Thoughts
    0.06
     delight
    0.06
     tim
    0.06
    ď
    0.06
    ongoose
    0.06
    ving
    0.06
    Activations Density 0.083%

    No Known Activations