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. 123484
    Prev
    Next
    INDEX
    Explanations

    -

    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
    ُس
    -0.07
    809
    -0.06
     OU
    -0.06
     эта
    -0.06
     надеж
    -0.06
     �
    -0.06
     fighter
    -0.06
     impeccable
    -0.06
    eron
    -0.06
    rather
    -0.06
    POSITIVE LOGITS
    (width
    0.07
     tvb
    0.07
    โปร
    0.07
    _IOC
    0.07
     solves
    0.07
    τιν
    0.07
     ناح
    0.06
    (mutex
    0.06
     dataSource
    0.06
    .Real
    0.06
    Activations Density 0.001%

    No Known Activations