© 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
    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. 42622
    Prev
    Next
    INDEX
    Explanations

    to be

    np_max-act · gemini-2.0-flash

    structured content about events or establishments related to beer and hospitality.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron selectively activates on instances of the copular verb “to be” (e.g. “is,” “it’s,” “are”).

    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
    quine
    -0.07
    (spell
    -0.07
    abble
    -0.07
    ething
    -0.07
     Violet
    -0.07
     Devices
    -0.06
    ctest
    -0.06
     peripherals
    -0.06
     loader
    -0.06
     bölüm
    -0.06
    POSITIVE LOGITS
    Sad
    0.07
     vyjád
    0.06
    Inf
    0.06
    ().__
    0.06
    BuilderInterface
    0.06
    'est
    0.06
    _inst
    0.06
     guaranteed
    0.06
    :!
    0.06
     abs
    0.06
    Activations Density 0.092%

    No Known Activations