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. 122125
    Prev
    Next
    INDEX
    Explanations

    binding

    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
     Sabb
    -0.07
    _like
    -0.06
     �
    -0.06
    Fuse
    -0.06
     těl
    -0.06
    til
    -0.06
    _scalar
    -0.06
     Hiro
    -0.06
     fuse
    -0.06
    -fire
    -0.06
    POSITIVE LOGITS
    \DependencyInjection
    0.07
    bindings
    0.07
     Binding
    0.07
    (forms
    0.07
     bindings
    0.07
    .sn
    0.07
    .handler
    0.06
    _loading
    0.06
    rt
    0.06
    );
    
    ↵
    0.06
    Activations Density 0.005%

    No Known Activations