© 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. 92861
    Prev
    Next
    INDEX
    Explanations

    greeting

    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
    enschaft
    -0.08
     capacities
    -0.07
    挑
    -0.07
    _EXTRA
    -0.07
     Panels
    -0.06
     chall
    -0.06
     下午
    -0.06
    algorithm
    -0.06
     channels
    -0.06
     physique
    -0.06
    POSITIVE LOGITS
     greet
    0.14
     greeted
    0.13
     greeting
    0.13
    reeting
    0.11
     greetings
    0.09
     fert
    0.08
    Greetings
    0.07
    reetings
    0.07
     grou
    0.07
     Throw
    0.07
    Activations Density 0.004%

    No Known Activations