© 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
    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. 104955
    Prev
    Next
    INDEX
    Explanations

    weighing or math problems

    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
    atan
    -0.07
     Bros
    -0.07
    leaning
    -0.06
    朗
    -0.06
    aries
    -0.06
     至
    -0.06
     러
    -0.06
    -send
    -0.06
     Robot
    -0.06
    하려
    -0.06
    POSITIVE LOGITS
     простран
    0.06
     noisy
    0.06
    GIT
    0.06
    dimensions
    0.06
    ("***
    0.06
    /il
    0.06
    оту
    0.06
     '')↵
    0.06
    ateau
    0.06
    ),
    0.06
    Activations Density 0.011%

    No Known Activations