© 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. 109839
    Prev
    Next
    INDEX
    Explanations

    elle

    np_max-act · gemini-2.0-flash

    The neuron fires strongly on the fragment “elle” in “Appellee(s),” i.e. it detects mentions of the appellee designation in court-opinion captions.

    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
    am
    -0.07
     얻
    -0.06
    AM
    -0.06
     TextAlign
    -0.06
    港
    -0.06
    _TMP
    -0.06
    _MAY
    -0.06
     Forty
    -0.06
    าประ
    -0.06
    GY
    -0.06
    POSITIVE LOGITS
     Hebrew
    0.07
     percussion
    0.07
     astrology
    0.07
     acompan
    0.07
     adipiscing
    0.07
     initializer
    0.07
    iture
    0.06
     Wired
    0.06
     handheld
    0.06
    กำ
    0.06
    Activations Density 0.003%

    No Known Activations