© 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. 55838
    Prev
    Next
    INDEX
    Explanations

    List

    np_max-act · gemini-2.0-flash

    The neuron is looking for the XML Property List (plist) file header/DOCTYPE declaration (the “<!DOCTYPE … plist PUBLIC … PropertyList-1.0.dtd>” region).

    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
    DEPEND
    -0.07
    .onload
    -0.06
    FAILURE
    -0.06
    �
    -0.06
     pow
    -0.06
    cession
    -0.06
    Atomic
    -0.06
    ','$
    -0.06
     نور
    -0.06
    conda
    -0.06
    POSITIVE LOGITS
     Penguins
    0.07
     skewed
    0.07
     sheriff
    0.07
    _frontend
    0.07
    backs
    0.06
    .single
    0.06
     aba
    0.06
    Positions
    0.06
     들어
    0.06
    .links
    0.06
    Activations Density 0.000%

    No Known Activations