© 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. 91968
    Prev
    Next
    INDEX
    Explanations

    generally

    np_max-act · gemini-2.0-flash

    This neuron responds to hedging or qualification words (e.g. “generally,” “typically,” “often”) that signal broad or non-strict statements.

    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
    uku
    -0.07
     lake
    -0.07
     highlight
    -0.06
     colour
    -0.06
     Ru
    -0.06
     Fuk
    -0.06
    خف
    -0.06
     useful
    -0.06
     soo
    -0.06
    four
    -0.06
    POSITIVE LOGITS
     generally
    0.16
     Generally
    0.11
    Generally
    0.09
    一般
    0.08
     geral
    0.08
     universally
    0.07
     一般
    0.07
     edilir
    0.07
     general
    0.07
     grop
    0.07
    Activations Density 0.019%

    No Known Activations