© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 96113
    Prev
    Next
    INDEX
    Explanations

    metadata descriptions

    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
    况
    -0.07
     needles
    -0.06
     Ordering
    -0.06
    анов
    -0.06
     solo
    -0.06
     binaries
    -0.06
    (insert
    -0.06
    クト
    -0.06
    ceased
    -0.06
     hunter
    -0.06
    POSITIVE LOGITS
     expresses
    0.07
     корп
    0.07
    ें↵
    0.06
     devised
    0.06
    vice
    0.06
    식을
    0.06
     Fleming
    0.06
    Ин
    0.06
     قتل
    0.06
    setProperty
    0.06
    Activations Density 0.028%

    No Known Activations