© 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. 11-RESID-POST-AA
    11. 102359
    Prev
    Next
    INDEX
    Explanations

    *b

    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
    got
    -0.07
     зат
    -0.07
     dün
    -0.06
     tř
    -0.06
     Steering
    -0.06
     /><
    -0.06
    erokee
    -0.06
     povin
    -0.06
    Techn
    -0.06
    omnia
    -0.05
    POSITIVE LOGITS
    ร
    0.07
    _interval
    0.06
     mM
    0.06
    _TAC
    0.06
    الات
    0.06
     realism
    0.06
    айте
    0.06
    _PUR
    0.06
    _MACHINE
    0.06
    	init
    0.06
    Activations Density 0.001%

    No Known Activations