© 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. 109498
    Prev
    Next
    INDEX
    Explanations

    due process

    np_max-act · gemini-2.0-flash

    legal terminology and concepts related to due process and fair treatment in employment situations.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron detects references to procedural due process or fair-hearing requirements (e.g., notice, hearing, due process, charges, procedure) in legal text.

    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
    -flow
    -0.06
    ле
    -0.06
    Flow
    -0.06
    fuck
    -0.06
     Trek
    -0.06
    Searching
    -0.06
     tái
    -0.06
    .converter
    -0.06
    Hundreds
    -0.06
    íd
    -0.06
    POSITIVE LOGITS
    setScale
    0.07
     Cookie
    0.07
    .QLabel
    0.07
    slot
    0.06
    QRSTUV
    0.06
     negatives
    0.06
    '=>['
    0.06
    purple
    0.06
     gravitational
    0.06
     standout
    0.06
    Activations Density 0.011%

    No Known Activations