© 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. 109774
    Prev
    Next
    INDEX
    Explanations

    lets

    np_max-act · gemini-2.0-flash

    This neuron fires on promotional product‐marketing language—especially positive feature‐describing adjectives and verbs like “ultra flexible,” “stunning,” “create,” and “easily.”

    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
    ologist
    -0.07
    .make
    -0.06
     Lloyd
    -0.06
    :**
    -0.06
     Future
    -0.06
     dispatched
    -0.06
     Panasonic
    -0.06
     psychiatrist
    -0.06
    truncate
    -0.06
     leagues
    -0.06
    POSITIVE LOGITS
    _keeper
    0.07
    uitar
    0.07
     @{@"
    0.06
    /engine
    0.06
     나
    0.06
     Separ
    0.06
    amat
    0.06
     договору
    0.06
     Dani
    0.06
     itu
    0.06
    Activations Density 0.226%

    No Known Activations