© 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. 23986
    Prev
    Next
    INDEX
    Explanations

    code

    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
     Changed
    -0.07
     пен
    -0.07
    Sr
    -0.06
     overlay
    -0.06
     unparalleled
    -0.06
     sharing
    -0.06
    )]↵↵
    -0.06
     visiting
    -0.06
    ;charset
    -0.06
     palindrome
    -0.06
    POSITIVE LOGITS
     віль
    0.06
    港
    0.06
    ослав
    0.06
    cannot
    0.06
    Cannot
    0.06
    	loop
    0.06
    	rv
    0.06
    Bei
    0.06
    χε
    0.06
     meas
    0.06
    Activations Density 0.080%

    No Known Activations