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. 85222
    Prev
    Next
    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect evaluative or descriptive adjectives (and related intensifiers) used in movie review text.

    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
    .dx
    -0.07
     đu
    -0.06
    jspb
    -0.06
    hdl
    -0.06
     vergi
    -0.06
    ์บ
    -0.06
    forces
    -0.06
    gle
    -0.06
    oku
    -0.06
     Dart
    -0.06
    POSITIVE LOGITS
    assador
    0.07
    .getRequestDispatcher
    0.06
    NU
    0.06
     />'
    0.06
     currentValue
    0.06
     个
    0.06
    UFF
    0.06
     surgeon
    0.06
    NAME
    0.06
     ще
    0.06
    Activations Density 0.066%

    No Known Activations