© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 130048
    Prev
    Next
    INDEX
    Explanations

    general information

    np_max-act · gemini-2.0-flash

    phrases related to creative professionals and their roles or experiences.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The main thing this neuron does is pick out adverbs and adverbial qualifiers (words like “rather,” “primarily,” “only,” “generally,” “now,” etc.) that modify or emphasize statements.

    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
     servings
    -0.07
     tub
    -0.07
    ORE
    -0.07
     Latitude
    -0.07
     Nagar
    -0.07
     も
    -0.07
    023
    -0.07
    ushort
    -0.07
    ある
    -0.06
    　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　
    -0.06
    POSITIVE LOGITS
     اصفه
    0.07
     NGX
    0.06
     nějak
    0.06
     junit
    0.05
     Anglic
    0.05
     ifad
    0.05
    conti
    0.05
     pneum
    0.05
     mentioning
    0.05
    alarına
    0.05
    Activations Density 0.005%

    No Known Activations