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. 84767
    Prev
    Next
    INDEX
    Explanations

    reference material

    np_max-act · gemini-2.0-flash

    This neuron responds to mentions of reference materials or external resources (e.g. tutorials, presentations, articles, blog posts, lecture notes).

    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
     bad
    -0.07
    苦
    -0.06
    getProperty
    -0.06
     bathing
    -0.06
    跑
    -0.06
     soccer
    -0.06
     distractions
    -0.06
     poor
    -0.06
     등
    -0.06
     codecs
    -0.06
    POSITIVE LOGITS
    _PER
    0.07
    룹
    0.06
     تاریخ
    0.06
    ']*
    0.06
    vtk
    0.06
     ALTER
    0.06
    із
    0.06
     Permit
    0.06
     Кур
    0.06
    .updated
    0.06
    Activations Density 0.051%

    No Known Activations