© 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. 126050
    Prev
    Next
    INDEX
    Explanations

    code/data

    np_max-act · gemini-2.0-flash

    financial terms and numeric calculations related to indemnification and liabilities.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron selectively activates on floating-point numeric tokens (decimal numbers).

    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
     lazy
    -0.07
     Sequelize
    -0.07
     Elena
    -0.07
     savory
    -0.06
     furry
    -0.06
     Gand
    -0.06
    sense
    -0.06
    .Tools
    -0.06
     موب
    -0.06
    AKE
    -0.06
    POSITIVE LOGITS
     okol
    0.06
    ,data
    0.06
     Produced
    0.06
     Verify
    0.06
    Namespace
    0.06
     regex
    0.06
     Adri
    0.06
    markup
    0.05
     ello
    0.05
     kamu
    0.05
    Activations Density 0.008%

    No Known Activations