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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15-RESID-POST-AA
    11. 90330
    Prev
    Next
    INDEX
    Explanations

    child speech

    np_max-act · gemini-2.0-flash

    sentences or tokens where the speaker introduces or refers to themselves (first-person self-reference / roleplay “I’m”, “my”, names and personal statements).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chewing
    -0.06
    لیت
    -0.06
     MH
    -0.06
    ###############################################################################↵
    -0.06
     misconduct
    -0.06
    ัล
    -0.06
    ;")↵
    -0.06
     takže
    -0.06
    ]')↵
    -0.06
     returnType
    -0.06
    POSITIVE LOGITS
    Buffers
    0.06
    _bins
    0.06
     demean
    0.06
    ervention
    0.06
    ivě
    0.06
     rubbing
    0.06
    _DATABASE
    0.06
    μη
    0.06
    _eff
    0.06
     Xu
    0.06
    Activations Density 0.175%

    No Known Activations