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. 122731
    Prev
    Next
    INDEX
    Explanations

    sim

    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
    ('(
    -0.06
     Economy
    -0.06
    \Traits
    -0.06
     Magical
    -0.06
     июня
    -0.06
     示例
    -0.06
    openid
    -0.06
     insanely
    -0.06
     edad
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    constitution
    0.07
    _boost
    0.07
    Le
    0.06
     experimented
    0.06
    arris
    0.06
     tub
    0.06
    -phone
    0.06
     sund
    0.06
     Rosenstein
    0.06
     ساخته
    0.06
    Activations Density 0.152%

    No Known Activations