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. 11-RESID-POST-AA
    6. 84835
    Prev
    Next
    INDEX
    Explanations

    of

    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
    效
    -0.07
    _row
    -0.07
     Disclosure
    -0.06
    #af
    -0.06
     allegations
    -0.06
     otáz
    -0.06
     userManager
    -0.06
    Observer
    -0.06
    hur
    -0.06
     Monday
    -0.06
    POSITIVE LOGITS
    itized
    0.08
    やる
    0.06
    outing
    0.06
     wearable
    0.06
    abay
    0.06
    ))/(
    0.06
    ิศ
    0.06
    éis
    0.05
    )._
    0.05
    UART
    0.05
    Activations Density 0.000%

    No Known Activations