© 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. 90941
    Prev
    Next
    INDEX
    Explanations

    listening and responding

    np_max-act · gemini-2.0-flash

    This neuron primarily activates on occurrences of the verb “be” when used to give advice or instructions (e.g. “Be genuine,” “Be present,” etc.).

    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
    是在
    -0.07
     {{{
    -0.07
    iyeti
    -0.06
    dispatcher
    -0.06
     instruments
    -0.06
    LIBINT
    -0.06
    せる
    -0.06
    ifica
    -0.06
    $headers
    -0.06
    izada
    -0.06
    POSITIVE LOGITS
     Gallagher
    0.06
     clearTimeout
    0.06
    (nullable
    0.06
    -derived
    0.06
     Fam
    0.06
     Scandinavian
    0.06
     Gael
    0.06
     Authentication
    0.06
     이상
    0.06
     Nikon
    0.06
    Activations Density 0.041%

    No Known Activations