© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 38979
    Prev
    Next
    INDEX
    Explanations

    s

    np_max-act · gemini-2.0-flash

    The neuron fires on the “k” tokens in Go import paths (especially in “k8s.io/…” module paths), i.e. identifying Kubernetes-related import import path components.

    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
    month
    -0.06
    inois
    -0.06
    _pipeline
    -0.06
    เอก
    -0.06
     FAIL
    -0.06
     قوان
    -0.06
    	Buffer
    -0.06
     Zionist
    -0.06
    utedString
    -0.06
    _PIN
    -0.06
    POSITIVE LOGITS
    ส
    0.07
    kos
    0.07
    ěr
    0.07
    (s
    0.07
    SQLite
    0.07
     واس
    0.07
     bs
    0.07
    �p
    0.06
    Sac
    0.06
    جه
    0.06
    Activations Density 0.001%

    No Known Activations