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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 93108
    Prev
    Next
    INDEX
    Explanations

    -winning

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of specific demographic or vulnerable groups (e.g. schoolchildren, pregnant mothers, church parishioners).

    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
    ан
    -0.07
    CHK
    -0.06
     <<=
    -0.06
    _CAL
    -0.06
     START
    -0.06
     warn
    -0.06
    ami
    -0.06
    Dean
    -0.06
     seeks
    -0.06
    That
    -0.06
    POSITIVE LOGITS
     conex
    0.07
    .BASE
    0.07
     ziyaret
    0.06
    okemon
    0.06
    Serialized
    0.06
     بنی
    0.06
    ellation
    0.06
     ctxt
    0.06
     ventas
    0.06
     governed
    0.06
    Activations Density 0.073%

    No Known Activations