© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 91483
    Prev
    Next
    INDEX
    Explanations

    94

    np_max-act · gemini-2.0-flash

    The neuron primarily fires on common small “function” words (e.g. articles and prepositions like a, the, in, of, with) in these technical/patent‐style documents.

    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
    mu
    -0.07
     Fiat
    -0.06
     Astr
    -0.06
    ीएम
    -0.06
    	def
    -0.06
    herit
    -0.06
    ücret
    -0.06
    _symbols
    -0.06
    erten
    -0.06
    tadır
    -0.06
    POSITIVE LOGITS
     negativity
    0.06
     inflater
    0.06
     Britann
    0.06
    lac
    0.06
     QMainWindow
    0.06
     Bắc
    0.06
     Unlimited
    0.06
     DOI
    0.06
     beforeEach
    0.06
     vrch
    0.06
    Activations Density 0.073%

    No Known Activations