© 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. 79106
    Prev
    Next
    INDEX
    Explanations

    been

    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
     MotionEvent
    -0.08
    dan
    -0.07
     Rain
    -0.07
     Dut
    -0.07
    PEED
    -0.07
    speed
    -0.06
    Spider
    -0.06
     carrot
    -0.06
     Timber
    -0.06
     amel
    -0.06
    POSITIVE LOGITS
    /map
    0.07
    Pe
    0.06
     một
    0.06
    _prim
    0.06
    之
    0.06
    omain
    0.06
    /location
    0.06
    оглас
    0.06
    เภ
    0.06
     جستارهای
    0.05
    Activations Density 0.001%

    No Known Activations