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. 3-RESID-POST-AA
    6. 94354
    Prev
    Next
    INDEX
    Explanations

    ciphertext

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     motivate
    -0.07
     travelers
    -0.07
     따라
    -0.06
     AUX
    -0.06
    Trigger
    -0.06
     artículo
    -0.06
    Indicator
    -0.06
    534
    -0.06
    kili
    -0.06
     criticize
    -0.06
    POSITIVE LOGITS
    rootScope
    0.16
     plaintext
    0.14
     oily
    0.14
     ciphertext
    0.14
     unequiv
    0.13
    runtime
    0.10
    iphertext
    0.10
    (inplace
    0.08
     reinst
    0.08
    ű
    0.07
    Activations Density 0.003%

    No Known Activations