© 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. 73746
    Prev
    Next
    INDEX
    Explanations

    chemical formulas

    np_max-act · gemini-2.0-flash

    The neuron detects subword pieces that occur in complex chemical compound names (i.e. IUPAC‐style nomenclature fragments).

    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
    izational
    -0.07
    Screenshot
    -0.06
    pler
    -0.06
     newcomers
    -0.06
    ostel
    -0.06
    -chief
    -0.06
    :invoke
    -0.06
    Subscriber
    -0.06
    agnost
    -0.06
    ुई
    -0.06
    POSITIVE LOGITS
     DAG
    0.07
     Distrib
    0.07
    column
    0.07
     Sexo
    0.07
     ráp
    0.07
    ignment
    0.07
     gracias
    0.07
     موفق
    0.07
     narrower
    0.07
     잡담
    0.06
    Activations Density 0.014%

    No Known Activations