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. 84463
    Prev
    Next
    INDEX
    Explanations

    hidden

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of hidden form fields (i.e. the word “hidden” in the context of input/field elements).

    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
    —↵↵
    -0.06
     Trump
    -0.06
     вік
    -0.06
    @test
    -0.06
    .pivot
    -0.06
     Lobby
    -0.06
    publish
    -0.06
     lên
    -0.06
    Tuple
    -0.06
     loops
    -0.06
    POSITIVE LOGITS
     timezone
    0.07
    алів
    0.06
     Jonah
    0.06
     син
    0.06
    چ
    0.06
     тих
    0.06
     Ron
    0.06
    อห
    0.06
     FH
    0.06
     MediaQuery
    0.06
    Activations Density 0.002%

    No Known Activations