© 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. 6744
    Prev
    Next
    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash

    The neuron fires on numerical measurements and comparisons—especially decimal or floating-point values in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    terms related to hypertension and its detection issues.

    oai_token-act-pair · gpt-4o-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
    Constructed
    -0.08
    countries
    -0.07
    사는
    -0.07
     Flags
    -0.07
    �
    -0.07
     invented
    -0.07
     algebra
    -0.06
    lexport
    -0.06
     occupational
    -0.06
     transparency
    -0.06
    POSITIVE LOGITS
    Meanwhile
    0.06
    인데
    0.06
    DAL
    0.06
    "}},↵
    0.06
     ek
    0.06
    ذ
    0.06
    续
    0.06
    pf
    0.06
     Аль
    0.06
     enticing
    0.06
    Activations Density 0.006%

    No Known Activations