© 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. 3-RESID-POST-AA
    6. 121623
    Prev
    Next
    INDEX
    Explanations

    academic and professional texts

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    女
    -0.06
    ляется
    -0.06
    祥
    -0.06
    лу
    -0.06
     baths
    -0.06
     fulfil
    -0.06
     спортив
    -0.06
    (customer
    -0.06
     đài
    -0.05
    ROOM
    -0.05
    POSITIVE LOGITS
     familiarity
    0.07
     indebted
    0.06
     ціл
    0.06
     LLC
    0.06
     CPP
    0.06
    dim
    0.06
     bingo
    0.06
    需求
    0.06
    (cl
    0.06
    _hex
    0.06
    Activations Density 0.684%

    No Known Activations