© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 7808
    Prev
    Next
    INDEX
    Explanations

    young

    np_max-act · gemini-2.0-flash

    The neuron fires on subjective, promotional adjectives (e.g. “special,” “natural,” “slate,” “curated”) used to describe or sell products.

    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
    (ev
    -0.07
    _sz
    -0.06
     Essen
    -0.06
     swim
    -0.06
    -ap
    -0.06
     humili
    -0.06
     Wishlist
    -0.06
     lead
    -0.06
     dazzling
    -0.06
    (sem
    -0.06
    POSITIVE LOGITS
    、“
    0.06
    ्तव
    0.06
    heatmap
    0.06
     tục
    0.06
    Neil
    0.06
     François
    0.06
    ANT
    0.06
    .Interfaces
    0.06
    selectAll
    0.06
    чук
    0.06
    Activations Density 0.241%

    No Known Activations