© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 110344
    Prev
    Next
    INDEX
    Explanations

    published

    np_max-act · gemini-2.0-flash

    The neuron detects publication status markings in court opinions (e.g. the word “Published” or “Slip Op.”).

    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
     Violence
    -0.06
     Text
    -0.06
    (Str
    -0.06
    Fld
    -0.06
     Armor
    -0.06
     Maze
    -0.06
    eve
    -0.06
     violence
    -0.06
    BinContent
    -0.06
     Exodus
    -0.06
    POSITIVE LOGITS
     chví
    0.07
    packed
    0.06
    zz
    0.06
     aws
    0.06
     доктор
    0.06
    раст
    0.06
     zwischen
    0.06
    ´s
    0.06
    (rx
    0.06
    ाय
    0.06
    Activations Density 0.007%

    No Known Activations