© 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. 13470
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on common function words (articles, prepositions, conjunctions, and auxiliary verbs) rather than content words.

    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
     Jab
    -0.06
    them
    -0.06
    ifier
    -0.06
     basin
    -0.06
     Peanut
    -0.06
    ONG
    -0.06
    interaction
    -0.06
    ipient
    -0.06
    ług
    -0.06
    ungs
    -0.06
    POSITIVE LOGITS
     #[
    0.07
    )(__
    0.07
    ’l
    0.06
    Cor
    0.06
    χει
    0.06
     Haziran
    0.06
     Hij
    0.06
    _vertical
    0.06
     ⓘ
    0.06
    Flow
    0.06
    Activations Density 0.068%

    No Known Activations