© 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. 43397
    Prev
    Next
    INDEX
    Explanations

    sec/section

    np_max-act · gemini-2.0-flash

    The neuron detects tokens that mark section or subsection headers (e.g. “SEC,” “Section,” numeric section numbers) in legal or legislative text.

    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
     cliff
    -0.06
     lawmakers
    -0.06
    ddf
    -0.06
    \db
    -0.06
    elfare
    -0.06
     Griffin
    -0.06
    	sl
    -0.06
     Clo
    -0.06
    TestFixture
    -0.06
     범
    -0.06
    POSITIVE LOGITS
    last
    0.06
     sost
    0.06
    (extra
    0.06
     départ
    0.06
    aktiv
    0.06
     Last
    0.06
     Turning
    0.06
     centrif
    0.06
    nnen
    0.06
    onden
    0.06
    Activations Density 0.003%

    No Known Activations