© 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. 7-RESID-POST-AA
    11. 119785
    Prev
    Next
    INDEX
    Explanations

    spaghetti

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    การณ
    -0.08
    Retrieve
    -0.07
     OSError
    -0.07
    HEME
    -0.07
    zel
    -0.06
    Merge
    -0.06
     chỗ
    -0.06
    336
    -0.06
     distraction
    -0.06
    DeviceInfo
    -0.06
    POSITIVE LOGITS
     mesmer
    0.06
    mort
    0.06
    ’nin
    0.06
     rubbish
    0.06
     repos
    0.06
    ']))
↵
    0.06
    ertura
    0.06
    icies
    0.05
     Tomáš
    0.05
     hete
    0.05
    Activations Density 0.389%

    No Known Activations