© 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. 128887
    Prev
    Next
    INDEX
    Explanations

    ride

    np_max-act · gemini-2.0-flash

    The neuron detects words and phrases related to vehicle suspension and ride quality (e.g. smooth, ride, comfort, suspension, road conditions).

    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
     darkness
    -0.07
    _destroy
    -0.07
    CallableWrapper
    -0.06
     dinheiro
    -0.06
    arta
    -0.06
     zak
    -0.06
    Ultimately
    -0.06
     abandoned
    -0.06
     spins
    -0.06
     Zhu
    -0.06
    POSITIVE LOGITS
    elden
    0.06
     Premier
    0.06
    -rounded
    0.06
    roulette
    0.06
    -Mart
    0.06
     ride
    0.06
    �은
    0.05
     atleast
    0.05
    -Петерб
    0.05
    ukkan
    0.05
    Activations Density 0.006%

    No Known Activations