© 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. 90870
    Prev
    Next
    INDEX
    Explanations

    inter

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of “sinter” (as in “sintering” or “sintered”), i.e. mentions of the sintering process.

    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
     sync
    -0.06
     tran
    -0.06
     Wave
    -0.06
     granny
    -0.06
    这样
    -0.05
     DMA
    -0.05
     Sync
    -0.05
     share
    -0.05
     Bronx
    -0.05
    /qu
    -0.05
    POSITIVE LOGITS
     nev
    0.08
    pest
    0.07
    іт
    0.07
     fict
    0.07
     krit
    0.07
     precio
    0.07
     SUCCESS
    0.07
     ELECT
    0.07
    administr
    0.07
     prior
    0.06
    Activations Density 0.002%

    No Known Activations