© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 126573
    Prev
    Next
    INDEX
    Explanations

    ing

    np_max-act · gemini-2.0-flash

    The neuron activates on gerund-style action words ending in “-ing.”

    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
     genomes
    -0.07
    Markers
    -0.07
    (timer
    -0.07
    dos
    -0.06
    ological
    -0.06
     termination
    -0.06
     Adjustable
    -0.06
     xcb
    -0.06
    илось
    -0.06
    TypeID
    -0.06
    POSITIVE LOGITS
     stacking
    0.08
    writing
    0.07
     matching
    0.07
     editing
    0.07
     decoding
    0.07
    idding
    0.07
     yelling
    0.07
    otyping
    0.07
     conven
    0.07
     Ging
    0.07
    Activations Density 0.180%

    No Known Activations