© 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. 53076
    Prev
    Next
    INDEX
    Explanations

    assets

    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
    杰
    -0.07
     tấm
    -0.07
     Soros
    -0.07
     telev
    -0.06
    澳
    -0.06
    advisor
    -0.06
    _sink
    -0.06
     CMS
    -0.06
     天
    -0.06
     Bac
    -0.06
    POSITIVE LOGITS
    .tiles
    0.08
    :NSLayout
    0.07
     tq
    0.07
    perimental
    0.06
    	length
    0.06
    |)↵
    0.06
    BitFields
    0.06
     acts
    0.06
     Matrix
    0.06
     qualification
    0.06
    Activations Density 0.052%

    No Known Activations