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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 92434
    Prev
    Next
    INDEX
    Explanations

    .googleapis

    np_max-act · gemini-2.0-flash

    The neuron detects CDN URLs (e.g. script src strings pointing to ajax.googleapis.com or maxcdn.bootstrapcdn.com).

    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
    _Page
    -0.06
    .eng
    -0.06
    _Password
    -0.06
     Circle
    -0.06
     دن
    -0.06
    cych
    -0.06
    /www
    -0.06
     fermentation
    -0.06
    chars
    -0.06
     форму
    -0.06
    POSITIVE LOGITS
    .googleapis
    0.07
    ezier
    0.07
    HIP
    0.07
    iei
    0.07
    entiful
    0.07
    umat
    0.06
     بال
    0.06
    ीख
    0.06
     pleas
    0.06
    ект
    0.06
    Activations Density 0.000%

    No Known Activations