© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 41064
    Prev
    Next
    INDEX
    Explanations

    Additionally

    np_max-act · gemini-2.0-flash

    The neuron fires on discourse connector adverbs (e.g., “Additionally,” “Furthermore,” “Moreover”) that introduce new points or continue an argument.

    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
    getMock
    -0.07
     orbits
    -0.07
     go
    -0.07
    :'',
    -0.07
    ROUTE
    -0.07
     KeyCode
    -0.07
    :@
    -0.07
     CLUB
    -0.06
     �
    -0.06
    470
    -0.06
    POSITIVE LOGITS
     Additionally
    0.13
    Additionally
    0.11
     bền
    0.08
     एड
    0.08
     Madd
    0.07
    団
    0.07
     adulte
    0.07
     +
    0.07
    anson
    0.07
     Tenn
    0.07
    Activations Density 0.031%

    No Known Activations