© 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. 13770
    Prev
    Next
    INDEX
    Explanations

    mouse clicks and events

    np_max-act · gemini-2.0-flash

    code snippets for Angular directives related to table interactions.

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

    The neuron fires on terms naming user‐interaction events or gestures (e.g. click, tap, wheel, gesture).

    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
     पड
    -0.06
     시간
    -0.06
    estinal
    -0.06
    .Children
    -0.06
     degli
    -0.06
     wind
    -0.06
     children
    -0.05
     sacram
    -0.05
     Geld
    -0.05
    +</
    -0.05
    POSITIVE LOGITS
    Classic
    0.06
    осп
    0.06
     ….
    0.06
    榜
    0.06
    _KeyPress
    0.06
    quotes
    0.06
    ceph
    0.06
     такой
    0.06
    PACKAGE
    0.06
    parable
    0.06
    Activations Density 0.004%

    No Known Activations