Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 129491
    Prev
    Next
    INDEX
    Explanations

    -icon

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on HTML link tags specifying favicons or Apple touch icons (e.g. “apple-touch-icon” and related size attributes).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    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
     veggies
    -0.06
    ières
    -0.06
     its
    -0.06
     rob
    -0.06
    ordinated
    -0.06
     damit
    -0.06
     Beginners
    -0.06
     Pride
    -0.05
     Regulations
    -0.05
    軟
    -0.05
    POSITIVE LOGITS
     naam
    0.08
     calcium
    0.07
     출
    0.07
     инт
    0.07
     annot
    0.07
    -icon
    0.07
    -O
    0.07
     çok
    0.07
    Graphics
    0.07
     oz
    0.07
    Activations Density 0.000%

    No Known Activations