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. 43691
    Prev
    Next
    INDEX
    Explanations

    Steel

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the word “steel.”

    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
    iná
    -0.07
    ags
    -0.06
     зна
    -0.06
    لیت
    -0.06
    顾
    -0.06
     Having
    -0.06
     Village
    -0.06
    DownLatch
    -0.06
    _report
    -0.06
    $update
    -0.06
    POSITIVE LOGITS
     Steel
    0.15
     steel
    0.14
    Steel
    0.13
    steel
    0.10
    EL
    0.08
    II
    0.08
    钢
    0.08
     ssl
    0.08
    740
    0.07
    ULL
    0.07
    Activations Density 0.004%

    No Known Activations