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. 100385
    Prev
    Next
    INDEX
    Explanations

    screen position/layout

    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
    lightbox
    -0.07
     спрос
    -0.07
    าจารย
    -0.07
    팔
    -0.06
    catalog
    -0.06
    JSONArray
    -0.06
    そう
    -0.06
    距離
    -0.06
     problémy
    -0.06
    불
    -0.06
    POSITIVE LOGITS
     statewide
    0.07
    .",↵
    0.06
     MN
    0.06
     enrol
    0.06
    으니
    0.06
    ruption
    0.06
    '=
    0.06
     jde
    0.06
    -MM
    0.06
    まと
    0.06
    Activations Density 0.015%

    No Known Activations