© 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. 13953
    Prev
    Next
    INDEX
    Explanations

    Negative events in a story

    np_max-act · gemini-2.0-flash

    The neuron strongly responds to verbs denoting crimes or other violent actions (e.g. kills, steals, kidnaps, throws blame).

    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
     stru
    -0.07
    ประเภท
    -0.06
    (created
    -0.06
     Amnesty
    -0.06
    وية
    -0.06
     probes
    -0.06
     DEALINGS
    -0.06
    ゼ
    -0.06
     Lös
    -0.06
     zus
    -0.06
    POSITIVE LOGITS
    shake
    0.07
    Ï
    0.06
    submit
    0.06
     gob
    0.06
    slt
    0.06
    .req
    0.06
    _spell
    0.06
    stairs
    0.06
     highlighted
    0.06
    (step
    0.06
    Activations Density 0.013%

    No Known Activations