© 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. 126566
    Prev
    Next
    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash

    This neuron primarily detects references to legal procedures and court actions (e.g. removal, appeal, proceedings, property disputes).

    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
     rational
    -0.07
    окол
    -0.07
     onItemClick
    -0.07
    ossa
    -0.06
    com
    -0.06
    aille
    -0.06
    rss
    -0.06
    plx
    -0.06
    trs
    -0.06
    INDEX
    -0.06
    POSITIVE LOGITS
     gleich
    0.08
     kami
    0.07
     Claudia
    0.07
     EL
    0.07
     zwar
    0.06
     vaccines
    0.06
     Dude
    0.06
    般
    0.06
     STEP
    0.06
    _he
    0.06
    Activations Density 0.011%

    No Known Activations