© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 24570
    Prev
    Next
    INDEX
    Explanations

    questions and answers

    np_max-act · gemini-2.0-flash

    tokens indicating a character speaking in a weak, whining or softly voiced manner (e.g., cues of whining/weak voice).

    oai_token-act-pair · gpt-5-mini
    Triggered 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
    Negative Logits
    "The
    -0.07
     Thanh
    -0.07
    Therefore
    -0.06
    рения
    -0.06
    庄
    -0.06
    IH
    -0.06
    	The
    -0.06
    +")
    -0.06
    '}}
    -0.06
     edited
    -0.06
    POSITIVE LOGITS
     textSize
    0.07
    .DateFormat
    0.07
    FormatException
    0.07
    .ico
    0.07
    _reference
    0.06
    xFFFF
    0.06
     dansk
    0.06
    äft
    0.06
    ckpt
    0.06
     wxT
    0.06
    Activations Density 0.462%

    No Known Activations