© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 28689
    Prev
    Next
    INDEX
    Explanations

    chairman

    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_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
     jist
    -0.07
    rep
    -0.07
     longitude
    -0.07
    ія
    -0.06
     producción
    -0.06
    rası
    -0.06
     Elle
    -0.06
    งหมด
    -0.06
     source
    -0.06
    ció
    -0.06
    POSITIVE LOGITS
     Chairman
    0.12
     chairman
    0.10
     jeden
    0.08
     Chair
    0.07
    _SPI
    0.07
     ratified
    0.07
     Guidance
    0.07
    .rpc
    0.07
    golden
    0.06
    .Inv
    0.06
    Activations Density 0.009%

    No Known Activations