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. 128900
    Prev
    Next
    INDEX
    Explanations

    Precise measurements/resolution

    np_max-act · gemini-2.0-flash

    The neuron is tuned to detect floating‐point numeric values (decimal numbers) in the text.

    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
    Containers
    -0.07
    _connected
    -0.06
     bedroom
    -0.06
    First
    -0.06
     catalog
    -0.06
     catalogue
    -0.06
     Establish
    -0.06
     reliance
    -0.06
    blob
    -0.06
     Containers
    -0.06
    POSITIVE LOGITS
     Xxx
    0.07
    _SMS
    0.07
    �다
    0.07
    ธน
    0.07
    =========
    0.06
    가능
    0.06
    markt
    0.06
    mares
    0.06
    (shift
    0.06
     microtime
    0.06
    Activations Density 0.050%

    No Known Activations