© 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. 11-RESID-POST-AA
    11. 45519
    Prev
    Next
    INDEX
    Explanations

    peer

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Một
    -0.07
     affine
    -0.07
    .free
    -0.06
    392
    -0.06
    Mvc
    -0.06
    "default
    -0.06
     Irene
    -0.06
     แพ
    -0.06
    	RTE
    -0.06
     RAF
    -0.06
    POSITIVE LOGITS
     Respect
    0.08
     poetry
    0.07
    Repeat
    0.07
     Peaks
    0.07
    =key
    0.07
     bearings
    0.07
     Chili
    0.06
    Dir
    0.06
     FILTER
    0.06
     pupil
    0.06
    Activations Density 0.003%

    No Known Activations