© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 124398
    Prev
    Next
    INDEX
    Explanations

    Pluralization/Agent Noun

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tung
    -0.07
    �蛛
    -0.07
     Dix
    -0.06
    "]),↵
    -0.06
    دهای
    -0.06
     cir
    -0.06
     tela
    -0.06
    "title
    -0.06
     CActive
    -0.06
     wires
    -0.06
    POSITIVE LOGITS
     farmers
    0.08
     Farmer
    0.08
     Arkansas
    0.07
     Farmers
    0.07
     Kaiser
    0.07
    LAR
    0.06
    農
    0.06
    ernity
    0.06
    pes
    0.06
     Vernon
    0.06
    Activations Density 0.006%

    No Known Activations