© 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 EvalsExportsinterp-engineNEWAPI 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. 27742
    Prev
    Next
    INDEX
    Explanations

    data location

    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
    Packet
    -0.08
     lease
    -0.08
    finish
    -0.07
    _unit
    -0.07
     queryParams
    -0.07
    entin
    -0.07
    แพ
    -0.07
    	label
    -0.07
    ilinx
    -0.07
    oul
    -0.07
    POSITIVE LOGITS
    bled
    0.06
     topp
    0.05
    \Command
    0.05
     rins
    0.05
    ané
    0.05
    رس
    0.05
    аті
    0.05
    ="${
    0.05
     nig
    0.05
     lend
    0.05
    Activations Density 0.341%

    No Known Activations