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. 84742
    Prev
    Next
    INDEX
    Explanations

    protesters

    np_max-act · gemini-2.0-flash

    The neuron responds to terms and phrases describing protests and related police actions—e.g. protesters, demonstrations, dispersal, arrests.

    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
    _damage
    -0.07
    ального
    -0.07
    یستم
    -0.06
     Webcam
    -0.06
    atz
    -0.06
    -alone
    -0.06
    れ
    -0.06
     Planned
    -0.06
    调用
    -0.06
    .selector
    -0.06
    POSITIVE LOGITS
     ea
    0.07
    alla
    0.06
    íg
    0.06
     lehet
    0.06
     Avatar
    0.06
    YPD
    0.06
     physiological
    0.06
    كار
    0.06
    ưởng
    0.06
    Byte
    0.06
    Activations Density 0.010%

    No Known Activations