© 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. 45009
    Prev
    Next
    INDEX
    Explanations

    '

    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
     paranoia
    -0.07
     terse
    -0.07
    .ReadLine
    -0.07
    iliated
    -0.07
    .ReadAll
    -0.07
    	boolean
    -0.06
     raz
    -0.06
     absentee
    -0.06
    нення
    -0.06
     bartender
    -0.06
    POSITIVE LOGITS
     deprived
    0.06
    Cmd
    0.06
     Aware
    0.06
     encountering
    0.06
     Základní
    0.06
     Comple
    0.06
    раниц
    0.06
     equipped
    0.06
    .Do
    0.06
    Processes
    0.06
    Activations Density 0.000%

    No Known Activations