© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 13552
    Prev
    Next
    INDEX
    Explanations

    inserted into

    np_max-act · gemini-2.0-flash

    technical terms associated with electrical and mechanical connections.

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

    The neuron strongly activates on mechanical-assembly verbs describing parts being inserted, fitted, or retained in slots, holes, or other openings.

    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
    ิส
    -0.07
    ยก
    -0.06
     ข
    -0.06
     warned
    -0.06
    utations
    -0.06
    іл
    -0.06
    emarks
    -0.05
     EC
    -0.05
    대를
    -0.05
     Mek
    -0.05
    POSITIVE LOGITS
     lub
    0.08
    fo
    0.07
     dahil
    0.07
     contentValues
    0.07
     participant
    0.07
    났
    0.07
     viewController
    0.07
    .MainActivity
    0.06
    ())));↵
    0.06
     aster
    0.06
    Activations Density 0.013%

    No Known Activations