© 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. 25330
    Prev
    Next
    INDEX
    Explanations

    ided

    np_max-act · gemini-2.0-flash

    The neuron activates on the date‐announcement lines in legal opinions (e.g. “Decided on [Month] [Day], [Year]”), identifying the formal decision dates.

    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
     звер
    -0.07
     lash
    -0.06
    े�
    -0.06
     conte
    -0.06
    02
    -0.06
     بیش
    -0.06
     Discount
    -0.05
     Alert
    -0.05
     olmadı
    -0.05
     werde
    -0.05
    POSITIVE LOGITS
     quarterbacks
    0.08
    Foundation
    0.07
    ?)
    0.07
    mult
    0.07
     :]
    0.07
     sentimental
    0.07
    ...)↵
    0.07
     Elekt
    0.07
    љ
    0.07
     flowering
    0.07
    Activations Density 0.002%

    No Known Activations