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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 81374
    Prev
    Next
    INDEX
    Explanations

    ISE

    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
    ربه
    -0.06
    inth
    -0.06
     mocker
    -0.06
    έντ
    -0.06
    ighton
    -0.06
    ورت
    -0.06
     encode
    -0.06
    Pure
    -0.05
     Sherlock
    -0.05
     dong
    -0.05
    POSITIVE LOGITS
    _Is
    0.08
     обо
    0.07
     pozisyon
    0.07
    .ConnectionStrings
    0.07
     className
    0.07
    screen
    0.06
    ในส
    0.06
    "`↵↵
    0.06
    作为
    0.06
    )';↵
    0.06
    Activations Density 0.000%

    No Known Activations