© 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. 92490
    Prev
    Next
    INDEX
    Explanations

    caulking and sealing

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of caulking or sealant application and related repair or sealing instructions.

    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
    OutOf
    -0.08
     facade
    -0.07
    !='
    -0.07
     oversight
    -0.07
     milano
    -0.06
     zoals
    -0.06
     ESA
    -0.06
     hadde
    -0.06
    需要
    -0.06
     faced
    -0.06
    POSITIVE LOGITS
     Fires
    0.07
    خوان
    0.07
    vím
    0.06
     completion
    0.06
    anced
    0.06
     mỹ
    0.06
    葡
    0.06
    etchup
    0.06
    _^(
    0.06
     ground
    0.06
    Activations Density 0.007%

    No Known Activations