© 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. 15-RESID-POST-AA
    11. 23671
    Prev
    Next
    INDEX
    Explanations

    official star naming

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     merit
    -0.07
    超
    -0.07
    Cars
    -0.06
     المص
    -0.06
     fullest
    -0.06
     fileprivate
    -0.06
    محمد
    -0.06
    conditional
    -0.06
    Escape
    -0.06
     prefect
    -0.06
    POSITIVE LOGITS
    ]
↵
    0.07
    .waitKey
    0.07
    olvable
    0.06
    .accuracy
    0.06
     estoy
    0.06
    ưới
    0.06
     businesses
    0.06
    [root
    0.06
     celebrities
    0.06
    ainty
    0.06
    Activations Density 0.007%

    No Known Activations