© 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. 11-RESID-POST-AA
    6. 77007
    Prev
    Next
    INDEX
    Explanations

    Code/programming

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -pop
    -0.07
    StateMachine
    -0.07
     fandom
    -0.06
    oc
    -0.06
     "").
    -0.06
     //////
    -0.06
    ّم
    -0.06
    �
    -0.06
    ]].
    -0.06
    ké
    -0.06
    POSITIVE LOGITS
     motivational
    0.07
     snakes
    0.07
     calories
    0.07
     usuário
    0.06
    _accessible
    0.06
     snake
    0.06
    ategorie
    0.06
     complementary
    0.06
     Fat
    0.06
     interested
    0.06
    Activations Density 0.133%

    No Known Activations