© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 23269
    Prev
    Next
    INDEX
    Explanations

    ability or possibility

    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
    ugged
    -0.06
     look
    -0.06
    .Left
    -0.06
     spectral
    -0.06
    owane
    -0.06
    Hooks
    -0.06
    něné
    -0.06
    bootstrap
    -0.06
     Release
    -0.06
    ='+
    -0.06
    POSITIVE LOGITS
    сед
    0.07
    /sbin
    0.07
    .mapper
    0.06
    952
    0.06
    増
    0.06
     Gamma
    0.06
    .enemy
    0.06
    	LOG
    0.06
     전용면적
    0.06
    -demand
    0.06
    Activations Density 0.017%

    No Known Activations