© 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. 87252
    Prev
    Next
    INDEX
    Explanations

    13

    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
    altern
    -0.07
    olesterol
    -0.07
    GitHub
    -0.07
    樂
    -0.06
    quests
    -0.06
    .adapters
    -0.06
    刘
    -0.06
     protecting
    -0.06
    -fly
    -0.06
    っち
    -0.06
    POSITIVE LOGITS
    ise
    0.07
     relação
    0.06
     Applying
    0.06
     досяг
    0.06
     rects
    0.06
    '),↵↵
    0.06
    >',↵
    0.06
    -->
↵
    0.06
    exception
    0.06
     Says
    0.06
    Activations Density 0.009%

    No Known Activations