© 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. 91602
    Prev
    Next
    INDEX
    Explanations

    forms of "to be"

    np_max-act · gemini-2.0-flash

    This neuron fires on the assistant’s standard self-introduction/help offers—i.e. phrases like “I’m here to help/assist you.”

    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
    _reward
    -0.07
    Independent
    -0.06
     brittle
    -0.06
    혀
    -0.06
     Chic
    -0.06
    Pas
    -0.06
    isinin
    -0.06
    Tes
    -0.06
    Spin
    -0.06
     gm
    -0.06
    POSITIVE LOGITS
     exacerb
    0.07
     atheist
    0.06
    kB
    0.06
     escalated
    0.06
    Ž
    0.06
    -ready
    0.06
     gehen
    0.06
     буд
    0.06
     lda
    0.06
    odable
    0.06
    Activations Density 0.013%

    No Known Activations