© 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. 47304
    Prev
    Next
    INDEX
    Explanations

    asking questions

    np_max-act · gemini-2.0-flash

    first-person self-descriptions of personal experiences or problems, often including durations, frequencies, and symptoms or life circumstances.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    zeichnet
    -0.06
     Bakan
    -0.06
     retrospective
    -0.06
     minecraft
    -0.06
     　　　　　　　　　　　　　　　　
    -0.06
    ."},↵
    -0.06
     ErrorMessage
    -0.06
     Yer
    -0.06
    Defs
    -0.05
     reinforcement
    -0.05
    POSITIVE LOGITS
    ebb
    0.06
    [vertex
    0.06
    Vertex
    0.06
    ัตร
    0.06
    (sign
    0.06
    핑
    0.06
    (Student
    0.06
    _CONSOLE
    0.06
    -value
    0.06
    	EIF
    0.06
    Activations Density 0.130%

    No Known Activations