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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 36584
    Prev
    Next
    INDEX
    Explanations

    commercial products and services

    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
    	col
    -0.06
    upgrade
    -0.06
    drops
    -0.06
    χό
    -0.06
     dil
    -0.06
    ró
    -0.06
    table
    -0.06
     snork
    -0.06
    нич
    -0.06
    ert
    -0.06
    POSITIVE LOGITS
     Contracts
    0.07
    .OS
    0.06
     cling
    0.06
    _billing
    0.06
    UN
    0.06
    problem
    0.06
     ventured
    0.06
     :'
    0.06
    YLES
    0.06
     Engl
    0.06
    Activations Density 0.001%

    No Known Activations