© 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. 6828
    Prev
    Next
    INDEX
    Explanations

    lists and structured data

    np_max-act · gemini-2.0-flash

    This neuron specializes in detecting proper names of rivers or lakes.

    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
     adjacency
    -0.07
    anguages
    -0.07
     bốn
    -0.06
     تك
    -0.06
     перес
    -0.06
    .boot
    -0.06
     Independence
    -0.06
    blr
    -0.06
     stř
    -0.06
    _subtitle
    -0.06
    POSITIVE LOGITS
     totalTime
    0.06
    MainActivity
    0.06
     iam
    0.06
     Huffman
    0.06
    ần
    0.06
    upload
    0.06
     colormap
    0.06
     stripper
    0.06
    :";
    ↵
    0.06
    URLOPT
    0.06
    Activations Density 0.019%

    No Known Activations