© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 9513
    Prev
    Next
    INDEX
    Explanations

    descriptive

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prototypes
    -0.06
    bout
    -0.06
     timeout
    -0.06
     फल
    -0.06
    óż
    -0.06
     BFS
    -0.06
     Mirror
    -0.06
     $
    -0.06
     weakSelf
    -0.06
    Projectile
    -0.06
    POSITIVE LOGITS
     دي
    0.07
    ()]↵↵
    0.07
    حق
    0.06
    ايت
    0.06
     نصب
    0.06
     isteyen
    0.06
    */
    ↵
    0.06
    										↵
    0.06
     altı
    0.06
     natural
    0.06
    Activations Density 0.005%

    No Known Activations