© 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. 14174
    Prev
    Next
    INDEX
    Explanations

    over

    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
    omitempty
    -0.07
    basket
    -0.06
     valley
    -0.06
    ότητα
    -0.06
     Valley
    -0.06
     ав
    -0.06
    .poster
    -0.06
    ditor
    -0.06
    stery
    -0.06
     DateTimeOffset
    -0.06
    POSITIVE LOGITS
     Jaguars
    0.08
     Specialists
    0.07
    .writeInt
    0.06
     prive
    0.06
     SUCCESS
    0.06
    cur
    0.06
    anta
    0.06
     Write
    0.06
    �
    0.06
     Networks
    0.06
    Activations Density 0.000%

    No Known Activations