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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 81427
    Prev
    Next
    INDEX
    Explanations

    code files

    np_max-act · gemini-2.0-flash

    This neuron detects floating‐point numeric literals (decimal 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
     art
    -0.07
     분야
    -0.06
    .RowCount
    -0.06
    (layers
    -0.06
    (command
    -0.06
    яд
    -0.06
     exec
    -0.06
     günü
    -0.06
    Ed
    -0.06
    	ep
    -0.06
    POSITIVE LOGITS
    وليو
    0.07
    _NV
    0.06
    しています
    0.06
    iske
    0.06
    ASY
    0.06
    asic
    0.06
    maze
    0.06
     ore
    0.06
     अव
    0.06
     レディース
    0.06
    Activations Density 0.021%

    No Known Activations