© 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. 91642
    Prev
    Next
    INDEX
    Explanations

    Did

    np_max-act · gemini-2.0-flash

    sentences discussing well-known public figures and their relationships with one another.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on the “Did you…” question opener (i.e. instances of “Did you” at the start of a segment).

    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
    a
    -0.07
     Corn
    -0.07
    Corn
    -0.07
     nurture
    -0.07
    RES
    -0.07
     Auss
    -0.07
    ream
    -0.07
    	core
    -0.07
     Ara
    -0.07
    Venta
    -0.07
    POSITIVE LOGITS
     did
    0.15
     Did
    0.14
    Did
    0.13
    did
    0.10
     didn
    0.10
     Didn
    0.10
     DID
    0.10
    Didn
    0.09
    )did
    0.09
    didn
    0.08
    Activations Density 0.047%

    No Known Activations