© 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. 68305
    Prev
    Next
    INDEX
    Explanations

    discourse markers/pronouns

    np_max-act · gemini-2.0-flash

    This neuron fires on sentence-initial discourse markers or transitional adverbs (e.g. “However,” “And,” “Then,” “But,” “When,” etc.).

    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
    @GeneratedValue
    -0.07
    ekim
    -0.07
     vad
    -0.07
    uala
    -0.06
    bero
    -0.06
    _CAP
    -0.06
    madı
    -0.06
     booked
    -0.05
     einige
    -0.05
    vo
    -0.05
    POSITIVE LOGITS
     Hover
    0.08
     Defendants
    0.07
    players
    0.07
     stě
    0.07
    徒歩
    0.07
     skipped
    0.06
     Batman
    0.06
     Horizontal
    0.06
    واع
    0.06
     debts
    0.06
    Activations Density 0.032%

    No Known Activations