Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 966
    Prev
    Next
    INDEX
    Explanations

    Circuit

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of a “Circuit” in court case headings, i.e. references to appellate circuits in legal citations.

    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
    asyarak
    -0.07
    nete
    -0.07
    ++;↵↵
    -0.07
    ulators
    -0.07
    ον
    -0.07
    ướng
    -0.07
    _e
    -0.07
    _ptrs
    -0.06
    antro
    -0.06
    actly
    -0.06
    POSITIVE LOGITS
     relocated
    0.06
    utm
    0.06
    ignment
    0.06
    xin
    0.06
    _SY
    0.06
     قطع
    0.06
     attachments
    0.06
     Cisco
    0.06
    _dispatcher
    0.06
    ukarı
    0.06
    Activations Density 0.002%

    No Known Activations