© 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. 23529
    Prev
    Next
    INDEX
    Explanations

    is

    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
     ابتدا
    -0.06
     indica
    -0.06
     patří
    -0.06
    اقع
    -0.06
    ेह
    -0.06
     canceled
    -0.06
     attracted
    -0.06
     telev
    -0.06
     Bowen
    -0.06
    、、
    -0.06
    POSITIVE LOGITS
    .tools
    0.07
     nomin
    0.07
    �
    0.06
    istorical
    0.06
    puties
    0.06
     faaliyet
    0.06
    ({});↵
    0.06
    toHave
    0.06
    OptionsResolver
    0.06
    _lat
    0.06
    Activations Density 0.035%

    No Known Activations