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. 40503
    Prev
    Next
    INDEX
    Explanations

    materials

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of specific welding materials, equipment, and process names (e.g., cast iron, mild steel, oxy-acetylene torch, SMAW, FCAW).

    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
     Routes
    -0.07
    _delivery
    -0.07
     Shop
    -0.06
     routes
    -0.06
     fourteen
    -0.06
    _PREFIX
    -0.06
     armies
    -0.06
     شدن
    -0.06
    _cb
    -0.06
    elve
    -0.06
    POSITIVE LOGITS
     dansk
    0.07
     nbytes
    0.07
     unintended
    0.07
    )dealloc
    0.06
    encoder
    0.06
     Regina
    0.06
    porto
    0.06
     );↵↵↵
    0.06
    itta
    0.06
    VB
    0.06
    Activations Density 0.043%

    No Known Activations