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. 42137
    Prev
    Next
    INDEX
    Explanations

    Start of sentences

    np_max-act · gemini-2.0-flash

    This neuron fires on the very first word of a new sentence (i.e. it detects sentence-initial tokens).

    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
    DED
    -0.06
    otron
    -0.06
     MQTT
    -0.06
     那
    -0.06
    温度
    -0.06
    DBC
    -0.06
     SUV
    -0.06
    	Gtk
    -0.06
    답
    -0.06
    endet
    -0.05
    POSITIVE LOGITS
    î
    0.07
    /");↵
    0.07
    Ο
    0.07
    lij
    0.07
     رشته
    0.07
    ‡
    0.06
    )';↵
    0.06
     chast
    0.06
     relic
    0.06
    ccb
    0.06
    Activations Density 0.129%

    No Known Activations