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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 58989
    Prev
    Next
    INDEX
    Explanations

    I

    np_max-act · gemini-2.0-flash

    The neuron is primarily triggered by occurrences of the first‐person singular pronoun “I.”

    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
    _Size
    -0.07
     ऊपर
    -0.07
    ---------
    -0.07
    _SET
    -0.06
    Thomas
    -0.06
    Release
    -0.06
    _Thread
    -0.06
     acquaint
    -0.06
     AppMethodBeat
    -0.06
    ServletContext
    -0.06
    POSITIVE LOGITS
    :I
    0.07
     kari
    0.06
     IH
    0.06
     توص
    0.06
    ipers
    0.06
     Penalty
    0.06
    대표
    0.06
     ≈
    0.06
     Conservatives
    0.06
     Lane
    0.06
    Activations Density 0.054%

    No Known Activations