© 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. 16033
    Prev
    Next
    INDEX
    Explanations

    Subtract

    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
    їв
    -0.07
    ترل
    -0.07
    شر
    -0.06
    :min
    -0.06
    ίου
    -0.06
    routine
    -0.06
    >>>>>>>>
    -0.06
    ('*',
    -0.06
    чного
    -0.06
     حد
    -0.06
    POSITIVE LOGITS
     uncovered
    0.08
    employed
    0.07
     concerts
    0.07
    ugal
    0.07
    Entered
    0.06
    (IB
    0.06
     Metrics
    0.06
    SF
    0.06
    Sept
    0.06
    ranges
    0.06
    Activations Density 0.000%

    No Known Activations