© 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. 44756
    Prev
    Next
    INDEX
    Explanations

    overflow

    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
     NC
    -0.08
    NC
    -0.07
    	AT
    -0.07
    	TR
    -0.07
     Huge
    -0.07
    quet
    -0.07
    File
    -0.07
     close
    -0.07
    acist
    -0.07
     normalize
    -0.07
    POSITIVE LOGITS
     overflow
    0.09
     güvenilir
    0.07
    ++++++++++++++++
    0.06
    abilir
    0.06
    .overflow
    0.06
    setFlash
    0.06
     CrossRef
    0.06
    -sur
    0.06
    _grupo
    0.06
     flows
    0.06
    Activations Density 0.003%

    No Known Activations