© 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. 42672
    Prev
    Next
    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash

    The neuron detects legal‐style citations and reference numbers (e.g. volume/page reporter references, dates, docket numbers).

    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
    งของ
    -0.07
     speeches
    -0.07
    ่น
    -0.07
    organization
    -0.07
    _station
    -0.06
    ("{
    -0.06
    TEXT
    -0.06
    rs
    -0.06
    converted
    -0.06
    StringUtils
    -0.06
    POSITIVE LOGITS
    .opendaylight
    0.07
    ycastle
    0.07
    _RECE
    0.06
    ovny
    0.06
     аб
    0.06
     kla
    0.06
     buttonText
    0.06
     setInput
    0.06
     valign
    0.06
    ्‍
    0.06
    Activations Density 0.036%

    No Known Activations