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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 30323
    Prev
    Next
    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash

    The neuron activates on specialized technical or scientific terms—especially biochemical names and complex nouns or verbs with suffixes like ­-ase, ­-in, ­-ation, or ­-ing.

    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
    irectional
    -0.07
    icity
    -0.07
     всіх
    -0.07
     teaching
    -0.06
     mon
    -0.06
     Toe
    -0.06
     xamarin
    -0.06
     Anthony
    -0.06
     Mormons
    -0.06
     CPC
    -0.06
    POSITIVE LOGITS
    ]:↵↵↵
    0.07
    ),'
    0.06
    Enlarge
    0.06
     multi
    0.06
     FactoryGirl
    0.06
     traditionally
    0.06
    rails
    0.06
     ευ
    0.06
    dojo
    0.06
    ライン
    0.06
    Activations Density 0.329%

    No Known Activations