Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 26197
    Prev
    Next
    INDEX
    Explanations

    tutorial

    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
     forme
    -0.07
    639
    -0.07
     compounds
    -0.07
    。不
    -0.07
     seedu
    -0.07
     —↵↵
    -0.07
     expresses
    -0.06
    James
    -0.06
     positions
    -0.06
     روابط
    -0.06
    POSITIVE LOGITS
     Tutorial
    0.12
     tutorial
    0.10
    Tutorial
    0.09
    tutorial
    0.09
     tutorials
    0.09
     tutor
    0.08
     QtCore
    0.07
     nanny
    0.07
     educating
    0.07
    utorial
    0.07
    Activations Density 0.006%

    No Known Activations