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

    Neuronpedia

    Jacobian LensNEW
    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. 45115
    Prev
    Next
    INDEX
    Explanations

    music events

    np_max-act · gemini-2.0-flash

    concert announcements and promotional event details.

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

    The neuron strongly activates on place names, in particular music venues or concert locations.

    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
     ponds
    -0.06
     barren
    -0.06
    singleton
    -0.06
     luz
    -0.06
    GroupId
    -0.06
    SEMB
    -0.06
     aren
    -0.06
    _OM
    -0.06
     rij
    -0.06
    zan
    -0.06
    POSITIVE LOGITS
    Interested
    0.06
     asymmetric
    0.06
    ้น
    0.06
    ursal
    0.06
     dokument
    0.06
     rule
    0.06
    AXB
    0.06
     Rule
    0.05
     (::
    0.05
     Targets
    0.05
    Activations Density 0.020%

    No Known Activations