© 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. 24788
    Prev
    Next
    INDEX
    Explanations

    body

    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
     logical
    -0.07
    Lost
    -0.07
    Finish
    -0.07
    _maximum
    -0.07
     mushrooms
    -0.07
     displ
    -0.07
     suspect
    -0.07
    :get
    -0.07
    Model
    -0.06
    Mono
    -0.06
    POSITIVE LOGITS
    تا
    0.07
     jelly
    0.07
     v
    0.06
     بی
    0.06
    divid
    0.06
    umps
    0.06
    nictvím
    0.06
    ']}
    0.06
    ))-
    0.06
    inerary
    0.06
    Activations Density 0.021%

    No Known Activations