© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 95461
    Prev
    Next
    INDEX
    Explanations

    assistant

    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
     Singap
    -0.06
     �
    -0.06
    lands
    -0.06
    ......↵↵
    -0.06
     今
    -0.06
    .;.;
    -0.06
     AN
    -0.06
    .@
    -0.06
    .<
    -0.06
    ....↵↵
    -0.05
    POSITIVE LOGITS
    assistant
    0.10
     Assistant
    0.10
     assistant
    0.09
    Assistant
    0.08
     writ
    0.07
    Gradient
    0.07
     textbooks
    0.06
    Systems
    0.06
    -treated
    0.06
    extra
    0.06
    Activations Density 0.254%

    No Known Activations