© 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. 85748
    Prev
    Next
    INDEX
    Explanations

    language

    np_max-act · gemini-2.0-flash

    The neuron flags discourse about the exact wording or “language” of legal provisions (e.g. statutes, amendments, or regulations).

    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
    .asList
    -0.07
    луг
    -0.07
    Lets
    -0.07
     закуп
    -0.06
    μμα
    -0.06
    Deposit
    -0.06
    sheets
    -0.06
     подключ
    -0.06
     tbl
    -0.06
     İki
    -0.06
    POSITIVE LOGITS
     "(\<
    0.08
    ...(
    0.07
     (--
    0.07
     guardar
    0.07
     Dunk
    0.07
    ...',↵
    0.06
     Supern
    0.06
     leases
    0.06
     lange
    0.06
     Uniform
    0.06
    Activations Density 0.010%

    No Known Activations