© 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. 109844
    Prev
    Next
    INDEX
    Explanations

    until

    np_max-act · gemini-2.0-flash

    email correspondence related to household maintenance issues.

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

    The neuron activates on occurrences of “wait” (often paired with “until”) indicating instructions to pause or defer action until a specified time.

    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
     proton
    -0.07
    =search
    -0.07
    omega
    -0.07
     photon
    -0.07
     denote
    -0.06
    空
    -0.06
     angi
    -0.06
     photons
    -0.06
    −
    -0.06
    acje
    -0.06
    POSITIVE LOGITS
    .defineProperty
    0.06
     возможности
    0.06
     instituted
    0.06
    regor
    0.06
     προϊ
    0.06
    流量
    0.06
    _expire
    0.06
    ->[
    0.06
    Visited
    0.06
     Pyramid
    0.06
    Activations Density 0.009%

    No Known Activations