© 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. 610
    Prev
    Next
    INDEX
    Explanations

    BOARD

    np_max-act · gemini-2.0-flash

    This neuron detects the header metadata and section‐heading tokens (e.g. DOCKET NO., DATE, BOARD, ATTORNEY, APPELLANT) in legal decision documents.

    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
    ož
    -0.08
    /menu
    -0.07
    NC
    -0.07
    jection
    -0.07
    _MESSAGES
    -0.06
    ्त
    -0.06
    WARN
    -0.06
     داد
    -0.06
    -stats
    -0.06
     ठ
    -0.06
    POSITIVE LOGITS
    !,↵
    0.06
    //
    ↵
    ↵
    0.06
    '];?>"
    0.06
     "]"
    0.06
     settles
    0.06
     <%=
    0.06
    @Column
    0.06
    �재
    0.06
     calidad
    0.06
    (&(
    0.05
    Activations Density 0.000%

    No Known Activations