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. 80853
    Prev
    Next
    INDEX
    Explanations

    added/changed

    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
     stamps
    -0.07
     increasing
    -0.07
     shield
    -0.07
     interval
    -0.07
    Entr
    -0.07
     outskirts
    -0.06
     protective
    -0.06
     promoter
    -0.06
     국제
    -0.06
    .central
    -0.06
    POSITIVE LOGITS
    (笑
    0.07
    _crit
    0.06
     Freed
    0.06
    回来
    0.06
         
    0.06
    >'↵
    0.06
    .pth
    0.06
     predicts
    0.06
    (TABLE
    0.06
    obbled
    0.06
    Activations Density 0.015%

    No Known Activations