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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 130038
    Prev
    Next
    INDEX
    Explanations

    sha

    np_max-act · gemini-2.0-flash

    The neuron fires on the “sha” token in integrity attributes (i.e. the Subresource Integrity (SRI) hash prefixes).

    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
     recur
    -0.08
    Ger
    -0.07
    dou
    -0.07
    олуч
    -0.06
    Authenticate
    -0.06
    conexion
    -0.06
     USE
    -0.06
    ้าต
    -0.06
    privacy
    -0.06
    appear
    -0.06
    POSITIVE LOGITS
    .batch
    0.07
     komm
    0.07
     фінансов
    0.06
     환경
    0.06
     Animated
    0.06
     Rural
    0.06
     crear
    0.06
     Turkey
    0.06
     Deployment
    0.06
     desirable
    0.06
    Activations Density 0.000%

    No Known Activations