© 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. 19719
    Prev
    Next
    INDEX
    Explanations

    step

    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
    发生
    -0.06
     welche
    -0.06
    ällt
    -0.06
    全
    -0.06
     confined
    -0.06
    -native
    -0.06
     sowie
    -0.06
     noses
    -0.06
    OwnerId
    -0.06
    eil
    -0.05
    POSITIVE LOGITS
     stepped
    0.14
     stepping
    0.14
     Too
    0.07
    OPER
    0.07
    nd
    0.07
     hm
    0.07
     BRE
    0.07
    dropdown
    0.07
    ENCED
    0.07
     squ
    0.07
    Activations Density 0.008%

    No Known Activations