© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 25969
    Prev
    Next
    INDEX
    Explanations

    Tuple

    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
    系
    -0.06
     ciphertext
    -0.06
     horn
    -0.06
    scene
    -0.06
     sheds
    -0.06
      
    -0.06
    skip
    -0.06
     따라
    -0.06
    ALE
    -0.06
     teenage
    -0.06
    POSITIVE LOGITS
    .cleaned
    0.07
     serialVersionUID
    0.07
    .getLogin
    0.07
    ardım
    0.06
    ]byte
    0.06
    merchant
    0.06
     terribly
    0.06
     architectural
    0.06
     unequiv
    0.06
    ukarı
    0.06
    Activations Density 0.007%

    No Known Activations