© 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. 92039
    Prev
    Next
    INDEX
    Explanations

    to be

    np_max-act · gemini-2.0-flash

    This neuron detects linking and explanatory verbs (forms of “be,” “is,” “used,” etc.) that introduce or define concepts.

    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
    vac
    -0.06
    _req
    -0.06
    imde
    -0.06
    olecule
    -0.06
     hole
    -0.06
    струмент
    -0.06
    .viewmodel
    -0.06
    gettext
    -0.06
     Hole
    -0.06
    Capabilities
    -0.06
    POSITIVE LOGITS
     coordin
    0.07
    .ax
    0.07
    .eth
    0.07
     누구
    0.06
     benefiting
    0.06
     stm
    0.06
     TextFormField
    0.06
    cházet
    0.06
     Hunters
    0.06
    astered
    0.06
    Activations Density 0.113%

    No Known Activations