© 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. 7602
    Prev
    Next
    INDEX
    Explanations

    her his

    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
     hesitation
    -0.07
    style
    -0.07
    _puts
    -0.07
     snakes
    -0.07
    vec
    -0.07
     gained
    -0.07
    -fire
    -0.07
    periences
    -0.07
     Thumb
    -0.07
     kernel
    -0.07
    POSITIVE LOGITS
    :block
    0.06
    ».↵↵
    0.06
     assay
    0.06
     detox
    0.06
     nhưng
    0.05
     rocking
    0.05
    elcome
    0.05
     gồm
    0.05
    @hotmail
    0.05
     debit
    0.05
    Activations Density 0.018%

    No Known Activations