Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 26565
    Prev
    Next
    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of opening new windows or browser windows (e.g. calls to window.open).

    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
     sensed
    -0.06
     postponed
    -0.06
    40
    -0.06
    ett
    -0.06
    ices
    -0.06
    治疗
    -0.06
     Servers
    -0.06
     qualifier
    -0.06
    شار
    -0.06
    ывает
    -0.06
    POSITIVE LOGITS
     Repo
    0.07
     Geoff
    0.07
     tık
    0.07
     Orbit
    0.06
    .LEADING
    0.06
    ので
    0.06
    (exec
    0.06
    .npy
    0.06
    :Get
    0.06
     immac
    0.06
    Activations Density 0.087%

    No Known Activations