© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 13045
    Prev
    Next
    INDEX
    Explanations

    abroad

    np_max-act · gemini-2.0-flash

    the neuron is tuned to detect floating-point numerical values (decimal fractions) 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
    声音
    -0.07
     olması
    -0.06
     شهید
    -0.06
    ために
    -0.06
    /gl
    -0.06
     khác
    -0.06
     riots
    -0.06
    neys
    -0.06
    zeigen
    -0.06
    .operation
    -0.06
    POSITIVE LOGITS
     activists
    0.07
    анд
    0.07
    points
    0.07
     지난
    0.06
    宾
    0.06
    (un
    0.06
     xi
    0.06
    珍
    0.06
     stationed
    0.06
    acyj
    0.06
    Activations Density 0.000%

    No Known Activations